© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3779
    Prev
    Next
    INDEX
    Explanations

    statements related to drawing conclusions or making inferences from data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     auft
    -0.31
     Hamma
    -0.31
    ActivityCompat
    -0.30
    ご存知
    -0.30
    Tracce
    -0.30
    gdx
    -0.29
    cf
    -0.28
    +#+
    -0.28
    |}{
    -0.28
    ro
    -0.28
    POSITIVE LOGITS
     conclusion
    2.94
     conclusions
    2.77
    conclusion
    2.63
    Conclusion
    2.47
     Conclusions
    2.44
     Conclusion
    2.42
     conclude
    2.38
    Conclusions
    2.34
     conclu
    2.30
     conclusión
    2.25
    Activations Density 1.125%

    No Known Activations