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. 10917
    Prev
    Next
    INDEX
    Explanations

    declarations of integer variables in programming code

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

    Declaration of integers in C/C++ code

    np_acts-logits-general · gemini-2.0-flash

    integer declarations and usage

    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
    ?>">
    -0.80
     striking
    -0.76
    VersionUID
    -0.72
     ***/
    -0.71
    ,:);
    -0.69
    ::::::::
    -0.69
     Оно
    -0.68
     AssemblyTitle
    -0.67
     sexuales
    -0.66
    ️
    -0.65
    POSITIVE LOGITS
     ints
    0.61
    ttemberg
    0.59
     i
    0.57
    int
    0.56
     getInt
    0.56
    iNdEx
    0.53
    лова
    0.52
    fcntl
    0.52
    uition
    0.51
    eiras
    0.51
    Activations Density 0.053%

    No Known Activations