Gemma 2

2024-08 · text · generative · anchor

Open-weight language model family released at 2B, 9B and 27B, used in the corpus as a small to mid-size open baseline alongside Llama and Qwen.

Note

cited as "Gemma Team" with no organisation named in the reference entry, so developer is left empty rather than filled from outside the sources

Variants

Gemma 2 2B, Gemma 2 2B It, Gemma 2 9B, Gemma 2 27B, Gemma-2-27B-IT, Gemma-2-9B-IT, Gemma-2 9B Instruct

Findings

• IC-007Most LLMs do not align closely with human moral preferences on multilingual trolley problems
• IC-009LLM moral preferences show significant language sensitivity but not inequality toward low-resource languages
• IC-011Jailbreaking LLMs can reduce refusal rates and improve alignment with human preferences
• IC-012Sparse autoencoders uncover entity recognition directions in Gemma 2 and Llama 3.1 models that are causally relevant for knowledge refusal.
• IC-013Entity recognition directions regulate attention to entity tokens in attribute extraction heads in Gemma and Llama models.
• IC-014Sparse autoencoders can identify 'uncertainty' directions in the residual stream before an answer, which are predictive of incorrect responses.
• IC-029Large language models show conformity to group answers in multi-agent interactions
• IC-030Larger language models exhibit higher independence rates and lower conformity under some protocols
• IC-054Gemma 2 2B performance degrades substantially when routed through Gemma Scope SAEs, and SAE-based feature suppression causes broad cross-domain degradation rather than targeted knowledge removal
• IC-064The TD learning mechanism identified in Llama 3 70B generalizes to Gemma-2-27B and Qwen-2.5-72B across all three tasks
• IC-103LLMs' value rankings align with the universal human value hierarchy under most prompting conditions
• IC-104Value anchor prompting produces LLM value correlation structures that closely match the human circular value structure, while standard prompting does not
• IC-105Value anchoring produces a sinusoidal scoring pattern around the circular value structure, with scores decreasing as circular distance from the anchor increases
• IC-160Pythia-70m and Gemma-2-2b implement subject-verb agreement across a relative clause via a circuit of number detectors, PP/RC boundary detectors, and verb form promoters, with Gemma-2-2b additionally using NP number trackers
• IC-161Linear probes on Pythia-70m and Gemma-2-2b trained on the ambiguous Bias in Bios set rely on gender as a spurious feature, with gender accuracy far exceeding profession accuracy
• IC-162The majority of subject-verb agreement performance in Pythia-70m is explained by approximately 100 SAE feature nodes and in Gemma-2-2b by approximately 500 nodes, compared to approximately 1500 and 50000 neurons respectively
• IC-166A 1-dimensional subspace in a single layer encodes the context-versus-prior decision in Llama-3.1-8B, Gemma-2 9B, and Mistral-v0.3 7B, and setting this subspace steers the released (non-fine-tuned) models' behavior
• IC-174RAG reduces model abstention and LLMs hallucinate rather than abstain when the retrieved context is insufficient to answer the query
• IC-175Context-sufficiency performance is scale-dependent: larger LLMs achieve high accuracy with sufficient context but still answer correctly 35-62% of the time without it, while smaller models hallucinate or abstain even with sufficient context
• IC-198Safety-aligned LLMs (GPT-4, GPT-3.5, Gemma2-27b, GPT-4o, Gemma2-9b, Qwen2.5-72b, Mistral-7b, Mixtral-8x22b) are vulnerable to natural prompts semantically related to toxic seed prompts, with attack success rates of 82-99%
• IC-205Gemma 2's SAE features exhibit depth-dependent organization, with polysemantic features in early layers and persistent, matchable features in later layers
• IC-221GPT-4o ReAct success rate drops from 47% on synchronous to 11% on asynchronous planning tasks, and all other tested LLMs show equal or worse performance
• IC-243Bias ratio on certain multi-turn fairness tasks decreases with model size in the Gemma-2 and Qwen2.5 families
• IC-245Pretrained LLMs produce duration-dependent outputs that are incompatible with a discrete token interpretation
• IC-246Pretrained LLMs assign coherent semantic meaning to linear interpolations between token embeddings, extending the linear embedding hypothesis to the output space
• IC-247Pretrained LLMs are invariant to positional shifts but sensitive to duration scaling of the input
• IC-264All 18 evaluated LLMs fail to abstain when the provided context lacks the answer, with performance gaps of 13.6% to 68.4% relative to the original context
• IC-265Model families show extreme variation in detecting conflicting answers in inconsistent contexts, with phi-3 series at 5.8% average accuracy versus GPT-4 series at 89.35%
• IC-266GPT-4o drops from 96.3% closed-book accuracy to 47.5% when given counterfactual context that contradicts its parametric knowledge, far below the 95% human accuracy on the same items
• IC-296The degree to which SAE features are active at multiple residual-stream layers increases with model size in Pythia, Gemma 2, Llama 3.2, and GPT-2
• IC-298Weight similarity in open-source LLMs is organized in a depth-dependent structure with adjacent-layer similarity and distinct clusters at specific depths
• IC-299Instruction tuning preserves the weight-matrix structure of LLMs, with DOCS scores exceeding 0.7 across all matrices
• IC-322Past-tense reformulations of harmful requests bypass refusal training in eight released LLMs, while future-tense reformulations are substantially less effective
• IC-327Llama-3-8B-Instruct, Mistral-7B-Instruct-v0.3, and several other LLMs produce well-calibrated verbal confidence estimates on classification tasks
• IC-384Llama-3-8B-Instruct shows larger absolute gains from prompt optimization than the stronger Gemma-2-9B-IT, indicating that prompt-optimization benefit is inversely related to base model capability
• IC-433LLMs exhibit a non-monotonic ID-OOD performance gap (generalization valley) that peaks at intermediate task complexity
• IC-434The critical complexity at which LLMs over-rely on memorization shifts to higher task difficulty as model size increases
• IC-481Llama-3.1-8B and four other released LLMs reorganize their internal representations to reflect in-context graph structure in a sudden two-phase transition as context length increases
• IC-566Adding instruction-specific steering vectors to the residual stream improves instruction-following accuracy for Phi-3, Gemma 2 2B IT, Mistral 7B IT, and Gemma 2 9B IT across format, length, and word-specific constraints
• IC-567Steering vectors computed on instruction-tuned Gemma 2 models transfer to base Gemma 2 models, with cross-model steering outperforming same-model steering for Gemma 2 2B
• IC-592The log-likelihood layer in LLaMA-2-7B, LLaMA-2-7B-Chat, Vicuna-7B, and Mistral-7B-Instruct produces factually incorrect answers on TruthfulQA MC1 (817 samples) due to a misalignment between the output distribution and internal attention head representations, with LM-to-head-norm accuracy gaps of 24.23 to 40.68 points.

Shared mechanisms

• Circular representationalso in Gemini 1.0 Pro, GPT-2, GPT-4 / ChatGPT4 / GPT-4 Code Interpreter / GPT-4 Technical Report, Llama 3, Llama 3.1, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, TerraMind
• Depth-dependent structurealso in Baichuan 2, BERT, BLIP-2, BLOOM, Chameleon, CLIP / CLIP-ViT (LC), DeepFloyd IF, DeiT-III, DINO, DINOv2, Falcon, Gemma, GPT-2, GPT-J, GPT-NeoX-20B, Griffin, I3D, Idefics, InstructBLIP, LLaMA, Llama 2 / Llama 2 base, Llama 3, Llama 3.1, Llama 3.2, Llama-3.2-3B, LLaVA, LLaVA-1.5 / LLaVA-v1.5, LLaVA-Phi, MAE, MAE-B/16, Mamba, MiniGPT-4, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, Mixtral 8x7B / Mistral 8x7B Instruct / Mixtral 46.7B / Mixtral 8x7B Instruct / Mixtral-instruct-8x7b, mPLUG-Owl, MPT, MultiBERTs, MViT V2, OLMo / OLMo base, OpenCLIP, OPT, Phi-2, Pythia, Qwen 2, Qwen2-VL, Qwen2.5, RoBERTa / RoBERTa-L, RWKV, SALMONN, SAM, SlowFast, Stable Diffusion, Swin Transformer, TerraMind, TimesFormer, TSM, Uniformer, Vicuna, VideoMAE, ViT, X3D, Yi
• Distance preservationalso in CLIP / CLIP-ViT (LC), CoPlace, DINO, DINOv2, Gemma, ImageBind, LanguageBind, LLaMA, Llama 2 / Llama 2 base, Llama 3, Llama 3.1, Llama-3.2-3B, LLaVA-1.5 / LLaVA-v1.5, LLaVA-Med, MAE, MAE-B/16, OpenCLIP, Pythia, ResNet / ResNet-152 / ResNet-101 / ResNet-50-BN, SigLIP, SLIP, TerraMind, ViT
• Explanation faithfulnessalso in BakLLaVA, CF2, Claude 3, Claude 3.5, CLIP / CLIP-ViT (LC), DRUM, Fuyu, GEM, Gemini 1.5 / Gemini Pro 1.5, GPT-3.5 / ChatGPT-3.5, GPT-4 / ChatGPT4 / GPT-4 Code Interpreter / GPT-4 Technical Report, GPT-4o, GPT-J, Idefics, Llama 3.1, LLaVA-NeXT / LLaVA 1.6, MAE-B/16, MobileNetV2, mPLUG-Owl3, OpenFlamingo, PGExplainer, Pythia, RCExplainer, ResNet / ResNet-152 / ResNet-101 / ResNet-50-BN, SigLIP, SigLIP-2, Stable Diffusion, TAGExplainer, ViT
• Failure modealso in AASIST, ADM, Aegis-Guard-Defensive, Alpaca, AnyLoc, AutoTikZ / DataTikZ, Baichuan, Baichuan 2, Baichuan2-13B, BakLLaVA, Bard, BEiT, BERT, BingChat, BLIP, BLIP-2, BLOOM, BSRNet, CF2, Chat-UniVi-7B, ChatGLM-6B / ChatGLM-6b-2, ChatGLM2, ChatGPT, CLAP, Claude 1.3, Claude 2.0, Claude 2.1, Claude 3, Claude 3.5, CLEAR, CLIP / CLIP-ViT (LC), CLIP4Clip, CLIPBERT, CLIPCap, CLMBR-T-BASE, CloFNet, Code Llama, CodeGeex2, CodeGen, CodeLlama-13B, CodeLlama-34B, CogVLM2, Cohere Command R, CoMEt, Command R+, CONCH, CycleGAN, DALL-E, DALL·E 2, DALL·E 3, DASR, DECAF, DeepSeek-2-Chat, DeepSeek-2-Coder, DeepSeek-V2-0628, DeepSeek-VL, DeepSeek-VL2, DeiT, DeiT-III, Depth Anything, DETR-R50, DimeNet++, DINO, DINO-FocalNet-Large, DINOv2, EGNN, Emu2, EquiformerV2, ESCN, ESM-2, ESM3, ESRGAN, EVA-CLIP, EVE, Falcon, Faster R-CNN / Faster R-CNN R50 / Faster R-CNN X101, FLAN-T5, Florence-2, FLUX / FLUX1, FoveaBox, Fuyu, Galactica-6.7B, GAT, 3D Gaussian Splatting, GCN, Gemini, Gemini 1.5 / Gemini Pro 1.5, Gemma, GIN, GLIDE, GLM-4, GLM-4V, GloVe, GP-UNIT, GPT-2, GPT-3 / GPT base, GPT-3.5 / ChatGPT-3.5, GPT-4 / ChatGPT4 / GPT-4 Code Interpreter / GPT-4 Technical Report, GPT-4.1, GPT-4o, GPT-J, GPT-NeoX-20B, GraphSAGE, Grounding DINO, Guanaco, GVP, Hawkeye, HiFaceGAN, HPS, HuggingGPT, IDDPM, Idefics, Idefics2, ImageBind, ImageBind-LLM-7B, Imagen Video, ImageReward, 12-in-1, InstructBLIP, InstructGPT, InternLM-2.5-7B, InternLM-XComposer2-VL, InternVideo, InternVL-1.5, InternVL2, Koala, LegalBERT, LLaMA, Llama 2 / Llama 2 base, Llama 3, Llama 3.1, Llama 3.2, Llama-3.2-3B, Llama-3-2-Vision, LLaMA-Adapter v2, Llama Guard, Llama Guard 2, Llama-Guard 3, Llama-VID, LLaVA, LLaVA-1.5 / LLaVA-v1.5, LLaVA-Med, LLaVA-NeXT / LLaVA 1.6, LLaVA-OneVision, LongVA-7B, LOVT, LWM-1M-JAX, MACE, MAE, Med-Flamingo, Merlot Reserve, MGCA, MiDaS, MiniCPM-V, MiniGPT-4, Mip-Splatting, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, Mistral Large 2, Mistral Large V2, Mixtral, Mixtral 8x7B / Mistral 8x7B Instruct / Mixtral 46.7B / Mixtral 8x7B Instruct / Mixtral-instruct-8x7b, MobileNetV2, Molmo, MolmoE-7B, Momentor, Moondream2, Moonshot-v1-8k, mPLUG-2, mPLUG-Owl, mPLUG-Owl3, mPLUG-Owl2, MPT, MSA Transformer, MultiBERTs, Nova Canvas, Nova Lite, Nova Pro, O1 / OpenAI-o1-preview, O3, O4-mini, OLMo / OLMo base, OneLLM, OpenAI Moderation, OpenChat-3.5-0106, OpenCLIP, OpenFlamingo, OPT, Otter, Otter-7B, PaLM 2, PaLM 62B, PandaGPT-7B, PerSAM, Phi-3, Phi-3.5 Mini Instruct, PickScore, PLIP, Prismatic, ProGen-2, Pythia, Qwen1.5, Qwen 2, Qwen 2.5 72B Instruct, Qwen2-VL, Qwen-Audio, Qwen-VL, Qwen2.5, Qwen2-Audio, R2D2, RadFM, RCExplainer, RD-SR, RealESRNet, Reprover, ResNet / ResNet-152 / ResNet-101 / ResNet-50-BN, RetinaNet-R50, RivaGAN, RS-LDS, RT-1, RT-2, SALMONN, SAM, SAM 2, SAULLM 54B, Scaffold-GS, SchNet, Seed-LLaMA-8B, SGC, SIREN, Sketch Transformer, SLD-max, SLD-medium, SLD-strong, SLDS, SLIMG, SpeechGPT, SphereNet, SRResNet, Stable Diffusion, StackLLaMA, Starcoder, StegaStamp, StyleGAN2-ADA, Swin Transformer, T5, TD-MPC, TerraMind, TimeChat, TranceptionEVE, TreeRing, Tulu 2, UnifiedQA, UniPerceiver, UNITER, UniVL, Van Gogh Diffusion, VERA, VGG / VGG13, Vicuna, Video-Chat-7B, Video-ChatGPT, Video-LLaMA, Video-LLaMA-2-13B, Video-LLaVA, VideoCLIP, ViLA-8B, ViLBERT, VindLU, VioLET, ViRTex, ViT, ViV1T, VTG-LLM, WildGuard, Wizardlm, X-CLIP, X-InstructBLIP-7B, XGen-MM, Xlm-R, Zephyr-7B-beta
• Linear representationalso in BLOOM, Cambrian-1, Chameleon, CLIP / CLIP-ViT (LC), DINOv2, EVA-CLIP, Falcon, Gemma, GPT-2, GPT-J, HPSv2, ImageBind, InstructBLIP, LanguageBind, LLaMA, Llama 2 / Llama 2 base, Llama 3, Llama 3.1, Llama-3.2-3B, LLaVA-1.5 / LLaVA-v1.5, LLaVA-NeXT / LLaVA 1.6, MAE, Mamba, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, OLMo / OLMo base, OpenCLIP, Phi-3, PickScore, Pythia, Qwen2-VL, Qwen2.5, ResNet / ResNet-152 / ResNet-101 / ResNet-50-BN, SALMONN, SAM, SigLIP, TerraMind, Tulu 2, Vicuna, ViT
• Method artefactalso in Baichuan, CLIP / CLIP-ViT (LC), ConvNeXt, EfficientNet, Falcon, Gemma, GPT-2, GPT-3.5 / ChatGPT-3.5, GPT-4o, GPT-J, InternLM, Llama 2 / Llama 2 base, Llama 3, Llama 3.1, MAP-NEO, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, OLMo / OLMo base, OpenCLIP, OpenLLaMA, OPT, Pythia, Qwen1.5, Qwen 2, Qwen2.5, RedPajama, ResNet / ResNet-152 / ResNet-101 / ResNet-50-BN, Skywork, Stable Diffusion, StableLM, TerraMind, ViT, Yi, ZiYA2
• Positional biasalso in BERT, ChatGPT, Claude 3, Claude 3.5, Falcon, Fuyu, Gemini, Gemini 1.5 / Gemini Pro 1.5, Gemma, GLIDE, GPT-2, GPT-3.5 / ChatGPT-3.5, GPT-4 / ChatGPT4 / GPT-4 Code Interpreter / GPT-4 Technical Report, GPT-4.1, GPT-4o, GPT-J, InstructGPT, LLaMA, Llama 2 / Llama 2 base, Llama 3, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, Mixtral, Mixtral 8x7B / Mistral 8x7B Instruct / Mixtral 46.7B / Mixtral 8x7B Instruct / Mixtral-instruct-8x7b, MPT, O1 / OpenAI-o1-preview, O3, O4-mini, PaLM 2, Phi-3, Pythia, Qwen1.5, Qwen 2, Qwen 2.5 72B Instruct, Stable Diffusion, Sybil, Vicuna
• Scale-dependent behaviouralso in Aquila-7B, BEiT, BERT, BLOOM, Claude 2.1, Claude 3, Claude 3.5, CLIP / CLIP-ViT (LC), Code Llama, CodeGen, Cohere Command R, DeepSeek LLM, DeepSeekMoE, DeiT-III, DINO, DINOv2, EquiformerV2, ESCN, Falcon, FLAN-T5, Gemini 1.0 Pro, Gemini 1.5 / Gemini Pro 1.5, Gemma, GPT-2, GPT-3 / GPT base, GPT-3.5 / ChatGPT-3.5, GPT-4 / ChatGPT4 / GPT-4 Code Interpreter / GPT-4 Technical Report, GPT-4o, GPT-J, GPT-Neo, I3D, Idefics, InternLM-2.5-7B, InternLM-XComposer2-VL, InternLM2, InternVL-1.5, InternVL2, LLaMA, Llama 2 / Llama 2 base, Llama 3, Llama 3.1, Llama 3.2, Llama-3.2-3B, LLaVA-1.5 / LLaVA-v1.5, LLaVA-NeXT / LLaVA 1.6, LongVA-7B, MAE, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, Mixtral, Mixtral 8x7B / Mistral 8x7B Instruct / Mixtral 46.7B / Mixtral 8x7B Instruct / Mixtral-instruct-8x7b, Moirai, MPT, MViT V2, O1 / OpenAI-o1-preview, OLMo / OLMo base, OpenCLIP, OpenFlamingo, OpenLLaMA, OPT, PaLM 2, Phi-3, Platypus2-Instruct-70B, Pythia, Qwen, Qwen1.5, Qwen 2, Qwen 2.5 72B Instruct, Qwen2-VL, Qwen-Audio, Qwen2.5, RedPajama-INCITE, ResNet / ResNet-152 / ResNet-101 / ResNet-50-BN, SlowFast, Solar 10.7B, Stable Diffusion, StableLM, Swin Transformer, T5, TerraMind, text-ada-001, TigerBot-70B-Chat, TimesFormer, TSM, Tulu 2, Uniformer, Vicuna, VideoMAE, ViLA-8B, Wizardlm, X3D, XGLM, Xwin-LM-70B-v0.1, Yi
• Shortcutalso in BakLLaVA, BLIP-2, Claude 3, Claude 3.5, CLIP / CLIP-ViT (LC), CLIP4Clip, CLIPBERT, DALL·E 2, DALL·E 3, DeepSeek-VL2, Eurus-RM-7B, Falcon, FLUX / FLUX1, Gemini, Gemini 1.5 / Gemini Pro 1.5, Gemma, GPT-2, GPT-3 / GPT base, GPT-3.5 / ChatGPT-3.5, GPT-4 / ChatGPT4 / GPT-4 Code Interpreter / GPT-4 Technical Report, GPT-4o, GPT-J, iFlytekSpark-13B, InstructBLIP, Internlm2-Reward, InternVideo, InternVL2, LLaMA, Llama 2 / Llama 2 base, Llama 3, Llama-3-2-Vision, LLaVA, LLaVA-1.5 / LLaVA-v1.5, LLaVA-Med, LLaVA-NeXT / LLaVA 1.6, Med-Flamingo, Merlot Reserve, MiniGPT-4, Mistral 7B / Mistral / Mistral 3 7B / Mistral-0.2-7B / Mistral-v0.1, Mixtral, Mixtral 8x7B / Mistral 8x7B Instruct / Mixtral 46.7B / Mixtral 8x7B Instruct / Mixtral-instruct-8x7b, Molmo, mPLUG-2, mPLUG-Owl3, Nova Canvas, O1 / OpenAI-o1-preview, OpenCLIP, OPT, Otter, PaLM 62B, Pythia, Qwen, Qwen 2, Qwen-VL, Qwen2.5, RadFM, ResNet / ResNet-152 / ResNet-101 / ResNet-50-BN, Stable Diffusion, Swin Transformer, Sybil, TerraMind, Tulu 2, UniPerceiver, UniVL, Vicuna, Video-LLaMA, VideoCLIP, VindLU, VioLET, X-CLIP