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. 21-GEMMASCOPE-RES-16K
    6. 7108
    Prev
    Next
    INDEX
    Explanations

    HTML header tags indicating sections or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.79
    rrggbb
    -0.71
    ArgsConstructor
    -0.69
    ////////////////
    -0.62
    <h2>
    -0.61
    UpInside
    -0.60
    principalColumn
    -0.60
    󠁢
    -0.59
    antMatchers
    -0.58
     Defender
    -0.57
    POSITIVE LOGITS
    <h5>
    0.71
    <h6>
    0.60
    andidaten
    0.53
     transférez
    0.53
    Soorten
    0.52
    ‍♀️
    0.51
     biß
    0.48
    غم
    0.48
    知道
    0.47
    참고
    0.47
    Activations Density 0.071%

    No Known Activations