© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7026
    Prev
    Next
    INDEX
    Explanations

    curly braces and the "ngx" prefix, indicating the presence of code syntax related to the NGINX framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archiviato
    -0.77
    VERTISEMENT
    -0.70
     externi
    -0.69
     الرياضيه
    -0.69
    Glej
    -0.69
    VIAF
    -0.68
     Athe
    -0.67
     ویکی‌پدیای
    -0.66
     comuniques
    -0.66
    PERTIES
    -0.65
    POSITIVE LOGITS
    {
    1.61
    <h2>
    1.41
    <b>
    1.24
    <strong>
    1.23
    <h4>
    1.16
    <h3>
    1.11
    |}{
    1.06
    {
    1.02
    <h1>
    1.00
    <h5>
    1.00
    Activations Density 0.014%

    No Known Activations