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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105575
    Prev
    Next
    INDEX
    Explanations

    preprocessor directives and header file inclusions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     취
    -0.37
     pooled
    -0.36
     color
    -0.36
     PERRY
    -0.36
     poor
    -0.35
     COVID
    -0.35
     most
    -0.35
    astéro
    -0.35
     мәкал
    -0.34
    ARGB
    -0.34
    POSITIVE LOGITS
    ClInclude
    0.79
    MLLoader
    0.73
    dafx
    0.73
    RectangleBorder
    0.69
    ThroughAttribute
    0.65
    .*")]
    0.63
    endregion
    0.62
    ChildScrollView
    0.61
     kasarigan
    0.61
    VersionUID
    0.60
    Activations Density 0.041%

    No Known Activations