concept
active
concept:gemma-2-improving-open-language-models-at-a-practical-size-team-et-al-2024Gemma 2: Improving Open Language Models at a Practical Size (Team et al., 2024)
Paper describing Gemma 2 model family used in this study
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Shows the instruction effect, while shifting geometry, may not produce consistent generalization effects across model families.
- Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 (Lieberum et al., 2024)concept0.774Paper introducing GemmaScope SAEs used for Gemma-2 model experiments
- Scaling trends at larger scale.
- RLHF paper cited as a major fine-tuning technique used in commercial dialogue agents
- Fine-tuning method paper whose technique is used in the fine-tuning experiments
- Unlearning limited by model capability.
- Interpretation of probe vs judge gap.
- Survey of representation engineering methods cited as related work