© 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. 96268
    Prev
    Next
    INDEX
    Explanations

    This neuron does not activate for any of the shown tokens — it appears not to detect any consistent pattern (no meaningful feature).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     <>",
    -0.42
    yntaxException
    -0.36
     exportación
    -0.35
    zzleHttp
    -0.33
     féd
    -0.33
     polaire
    -0.33
    SaveChangesAsync
    -0.32
    Bibliograf
    -0.31
    endgroup
    -0.31
    ScopeManager
    -0.31
    POSITIVE LOGITS
    綜合報導
    0.62
     informée
    0.58
    TagMode
    0.56
     surla
    0.54
    ⓧ
    0.52
    Transkript
    0.52
    WriteLiteral
    0.50
    AddHtmlAttribute
    0.50
    providedIn
    0.49
    "?>
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.