© 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. 6536
    Prev
    Next
    INDEX
    Explanations

    mentions of large gatherings or events with significant attendance

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

    crowds or big guns

    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
     ModelExpression
    -0.43
     resourceCulture
    -0.36
     invokingState
    -0.32
    pośred
    -0.32
    Hozzáférés
    -0.31
    Xna
    -0.31
     díl
    -0.31
     ciência
    -0.28
    лосипе
    -0.28
     atsi
    -0.28
    POSITIVE LOGITS
     packed
    1.56
     crowds
    1.43
     crowded
    1.42
     crowd
    1.41
     Packed
    1.27
    crowd
    1.24
    packed
    1.22
     CROW
    1.21
     sold
    1.21
     overcrowded
    1.20
    Activations Density 0.049%

    No Known Activations