© 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. 20-GEMMASCOPE-RES-16K
    11. 11694
    Prev
    Next
    INDEX
    Explanations

    sentences that indicate conclusions or summaries within the text

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

    "In" followed by a concluding word

    np_acts-logits-general · gemini-2.0-flash

    In 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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.78
     myſelf
    -0.74
     ModelExpression
    -0.74
     MediatR
    -0.73
    HtmlAttribute
    -0.71
    PropertyChanging
    -0.70
     himſelf
    -0.70
     pleaſure
    -0.70
    __(/*!
    -0.70
     Shakspeare
    -0.69
    POSITIVE LOGITS
     conclusion
    2.42
    Conclusion
    2.22
     Conclusion
    2.16
    conclusion
    2.10
     summary
    2.05
     conclusión
    1.99
     conclude
    1.93
     CONCLUSION
    1.89
    CONCLUSION
    1.87
     Summary
    1.84
    Activations Density 0.331%

    No Known Activations