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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2122
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in code or programming structures

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

    Code delimiters and punctuation

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    MigrationBuilder
    -0.62
    EndContext
    -0.51
    UseVisualStyle
    -0.51
     navires
    -0.51
    ίδα
    -0.51
     sanitarias
    -0.50
    routeProvider
    -0.49
    liferay
    -0.47
     critères
    -0.47
    REFER
    -0.47
    POSITIVE LOGITS
    kins
    0.73
    lows
    0.68
     SANS
    0.67
    acs
    0.67
     SKS
    0.66
    makedirs
    0.66
     ARS
    0.65
    rcs
    0.64
     ings
    0.62
     getResources
    0.62
    Activations Density 0.038%

    No Known Activations