© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 46743
    Prev
    Next
    INDEX
    Explanations

    categories and classifications related to topics or items

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

    category: followed by labels

    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
    FXMLLoader
    -0.47
    posedge
    -0.46
     Fakten
    -0.40
     للاسماء
    -0.40
    ształ
    -0.40
    MessageInfo
    -0.40
    itudinal
    -0.39
    仕様
    -0.39
    dolu
    -0.39
    chastic
    -0.39
    POSITIVE LOGITS
     category
    1.04
     categorization
    0.95
     categorize
    0.93
     categories
    0.89
     categoría
    0.86
    category
    0.86
     Category
    0.85
     getCategory
    0.82
     categor
    0.80
     categoria
    0.79
    Activations Density 0.076%

    No Known Activations