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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15803
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements in code

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

    Code, comments, or numerical data

    np_acts-logits-general · gemini-2.0-flash

    comment and code punctuation

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Geſch
    -0.70
    ikusbot
    -0.69
    ſchaft
    -0.69
     Geiſt
    -0.67
    majánló
    -0.66
     beſch
    -0.65
    iſchen
    -0.64
    niſſe
    -0.63
    mpagne
    -0.62
     Waſſer
    -0.62
    POSITIVE LOGITS
    //
    0.79
    /
    0.71
     //
    0.59
     /
    0.53
    <strong>
    0.52
    <b>
    0.52
     (
    0.48
     —
    0.44
     •
    0.42
    -
    0.41
    Activations Density 0.079%

    No Known Activations