© 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. 31-GEMMASCOPE-RES-16K
    11. 12461
    Prev
    Next
    INDEX
    Explanations

    programming terms and functions related to app development

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

    code syntax elements and programming language tokens.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     periodically
    -0.38
     fully
    -0.35
    static
    -0.33
     "
    -0.33
     physically
    -0.32
     obviously
    -0.32
    ↵↵↵↵
    -0.31
     integrated
    -0.31
    <eos>
    -0.31
     recently
    -0.31
    POSITIVE LOGITS
     ModelExpression
    0.93
     للاسماء
    0.82
    MessageOf
    0.80
    出版年
    0.79
     GenerationType
    0.75
    الحياه
    0.73
    UnusedPrivate
    0.72
    ScopeManager
    0.72
    IsMutable
    0.69
    Bibitem
    0.69
    Activations Density 1.063%

    No Known Activations