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. 11-GEMMASCOPE-RES-16K
    6. 5578
    Prev
    Next
    INDEX
    Explanations

    programming-related property setters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])/
    -0.63
    aarrggbb
    -0.60
    ://"
    -0.59
    ()]);
    -0.59
    ])[
    -0.59
     /^[
    -0.59
    føring
    -0.57
    /"+
    -0.57
    ]={
    -0.56
    '])){
    
    -0.56
    POSITIVE LOGITS
    endphp
    0.85
    脚注の使い方
    0.79
    IntoConstraints
    0.73
    EndContext
    0.72
    ArgsConstructor
    0.69
     متعلقه
    0.64
    didSet
    0.63
    formik
    0.63
     ExecuteAsync
    0.62
    存于互联网档案馆
    0.62
    Activations Density 0.009%

    No Known Activations