© 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. 42322
    Prev
    Next
    INDEX
    Explanations

    specific references to individuals, particularly those with the initial "O" and their related achievements or contributions

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

    Oleg Bogopolski, Olivier Kamanda

    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
    SharedCtor
    -0.45
     obvious
    -0.40
    Karakteristik
    -0.39
    TintMode
    -0.37
    OGND
    -0.36
    Gambas
    -0.36
    JpaRepository
    -0.36
    ngdoc
    -0.35
    ACHUSET
    -0.35
     mey
    -0.34
    POSITIVE LOGITS
    hoeddwyd
    0.62
     للاسماء
    0.57
    tonode
    0.52
     saites
    0.49
    Tazama
    0.47
    lahoma
    0.47
    Посилання
    0.44
    __((
    0.44
    Hentet
    0.44
    outSlope
    0.43
    Activations Density 1.438%

    No Known Activations