© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 27991
    Prev
    Next
    INDEX
    Explanations

    code related to setting visual properties in programming or drawing contexts

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

    custom library fill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.43
    didSet
    -0.37
     neceſſ
    -0.36
    颠
    -0.35
    aussian
    -0.35
    </thead>
    -0.35
     loco
    -0.34
     vi
    -0.33
    Explanation
    -0.33
     lenker
    -0.33
    POSITIVE LOGITS
    penup
    0.59
     <>",
    0.57
    contentLoaded
    0.57
    🟤
    0.45
    ViewFeatures
    0.43
    SharedDtor
    0.43
    blende
    0.43
    colgroup
    0.42
    OGND
    0.42
     ComVisible
    0.41
    Activations Density 0.010%

    No Known Activations