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. 10851
    Prev
    Next
    INDEX
    Explanations

    programming languages and their associated codes or frameworks

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

    Code diff markers in code files

    np_acts-logits-general · gemini-2.0-flash

    code file paths

    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
    ">',
    -0.69
    XmlEnum
    -0.66
     Administrativna
    -0.65
    %";
    -0.64
    HtmlAttribute
    -0.58
    '>"
    -0.58
    .$,
    -0.57
     '\''
    -0.57
    .";
    
    -0.57
    SpringRunner
    -0.57
    POSITIVE LOGITS
    دانشنامهٔ
    0.75
    bootstrapcdn
    0.67
    #
    0.61
    WindowConstants
    0.59
     BoxDecoration
    0.55
    verwijspagina
    0.55
    Naissance
    0.55
     disambiguazione
    0.53
     NSCoder
    0.53
    file
    0.52
    Activations Density 0.038%

    No Known Activations