© 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. 111230
    Prev
    Next
    INDEX
    Explanations

    instances of the word "clean"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Ave
    -0.33
     Si
    -0.33
     Avenue
    -0.32
    govina
    -0.32
     benef
    -0.30
     Aven
    -0.30
     Fi
    -0.30
     estekak
    -0.29
     Bo
    -0.29
     
    -0.29
    POSITIVE LOGITS
    Autoritní
    0.75
     ModelExpression
    0.74
     utafitiHapana
    0.72
     enfans
    0.71
    queryInterface
    0.65
     Geiſt
    0.65
     increí
    0.65
     ویکی‌پدی
    0.64
     Wikimedijinoj
    0.64
    +#+#
    0.62
    Activations Density 0.000%

    No Known Activations