© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    phrases associated with statements of knowledge or conclusions

    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
     ModelExpression
    -0.65
    
    -0.56
     Monfieur
    -0.55
    endregion
    -0.54
     Chrift
    -0.51
     ſame
    -0.50
     Jefus
    -0.50
     själva
    -0.49
    帖最后由
    -0.48
    nameof
    -0.48
    POSITIVE LOGITS
    :✨
    0.45
    ScopeManager
    0.43
    越
    0.39
    ReusableCell
    0.38
    AutoScaleMode
    0.35
     ويكيپيديا
    0.33
    queryInterface
    0.33
    getParams
    0.33
     Lightboxes
    0.33
    Exploration
    0.32
    Activations Density 0.763%

    No Known Activations