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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 51811
    Prev
    Next
    INDEX
    Explanations

    technical terms and elements related to coding and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.65
    The
    -0.40
    <
    -0.36
    A
    -0.36
    <strong>
    -0.35
    [
    -0.34
    I
    -0.34
    1
    -0.34
    (
    -0.33
    ↵↵
    -0.33
    POSITIVE LOGITS
    ConstraintMaker
    0.75
     ब्रेकडाउन
    0.73
    httphttps
    0.71
     autorytatywna
    0.69
    KommentareTeilen
    0.69
    tagHelperRunner
    0.69
     estekak
    0.68
    ScopeManager
    0.68
     CreateTagHelper
    0.68
    MLLoader
    0.68
    Activations Density 31.788%

    No Known Activations