© 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. 31-GEMMASCOPE-RES-131K
    11. 21317
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and punctuation or formatting elements, indicating a focus on structure and presence in code snippets

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

    code parsing, type annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    fromnode
    -0.50
    tvguidetime
    -0.49
     avoient
    -0.49
    DoubleQuotes
    -0.48
     nakalista
    -0.46
     HasFactory
    -0.46
    WireFormat
    -0.45
     betweenstory
    -0.45
    setupUi
    -0.44
    
    -0.44
    POSITIVE LOGITS
    WEBPACK
    1.21
    Билгалдахарш
    0.79
     يتيمه
    0.62
    DOCTYPE
    0.44
     متعلقه
    0.42
    providedIn
    0.36
    Obrázky
    0.34
     كومونز
    0.33
     onOptions
    0.33
    TheReal
    0.32
    Activations Density 0.001%

    No Known Activations