© 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. 4-GEMMASCOPE-RES-16K
    11. 10847
    Prev
    Next
    INDEX
    Explanations

    web-related URLs and their usage in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."]
    -0.92
    >")
    -0.91
    )");
    -0.91
     myſelf
    -0.88
    razine
    -0.85
     }}$}
    -0.83
    ."</
    -0.82
    >");
    -0.82
    ...");
    -0.82
     themſelves
    -0.81
    POSITIVE LOGITS
    url
    2.27
     url
    1.66
    urls
    1.15
    URL
    1.06
     URL
    0.78
     urls
    0.75
    urt
    0.69
    WebMethod
    0.68
    ur
    0.67
    furl
    0.66
    Activations Density 0.089%

    No Known Activations