© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25080
    Prev
    Next
    INDEX
    Explanations

    elements related to API request building and handling

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

    Java/JavaScript method calls

    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
    ?;
    -0.66
    !;
    -0.66
    »;
    -0.61
    );
    -0.60
    °;
    -0.60
    ();
    -0.59
     '/';
    -0.59
    ()?;
    -0.58
    |;
    -0.57
    *;
    -0.57
    POSITIVE LOGITS
    Odkazy
    0.43
     AssemblyTitle
    0.42
     transfieras
    0.42
    makeText
    0.42
    AndEndTag
    0.41
    ArgsConstructor
    0.41
    ɵɵelementStart
    0.41
    findpost
    0.40
    ptid
    0.38
     Paglinawan
    0.38
    Activations Density 0.021%

    No Known Activations