© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7473
    Prev
    Next
    INDEX
    Explanations

    conclusions and summary phrases in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens "So" or "In" followed by a summary or conclusion

    np_acts-logits-general · gemini-2.0-flash

    conclusion or summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MediatR
    -0.65
     ModelExpression
    -0.61
    IndentedString
    -0.58
     firft
    -0.57
     мәкал
    -0.57
    RTDA
    -0.56
     itſelf
    -0.54
     AUSSI
    -0.54
     alfo
    -0.54
     الرياضيه
    -0.53
    POSITIVE LOGITS
     conclusion
    2.13
    Conclusion
    1.88
    conclusion
    1.86
     Conclusion
    1.86
     conclusión
    1.82
    Fazit
    1.76
     conclude
    1.76
     summary
    1.70
     Fazit
    1.66
     CONCLUSION
    1.65
    Activations Density 0.328%

    No Known Activations