Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 65327
    Prev
    Next
    INDEX
    Explanations

    queries and considerations related to online services and personal choices

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

    words followed by question marks

    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
    ########.
    -0.63
    ConstraintMaker
    -0.51
    GIVEREF
    -0.51
    nodoc
    -0.50
     dieß
    -0.48
     gärna
    -0.48
    principalColumn
    -0.47
    <![
    -0.47
     nemlig
    -0.47
    ".
    
    -0.47
    POSITIVE LOGITS
    ?
    2.84
    ؟
    2.13
    ?
    2.03
    ?"
    2.02
    ?”
    1.99
    ?)
    1.91
    ?</
    1.88
    ?}
    1.87
    ?
    
    1.86
    %?
    1.80
    Activations Density 1.912%

    No Known Activations