Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11140
    Prev
    Next
    INDEX
    Explanations

    technical details related to software build processes and error logs

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    error messages

    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
    DeleteBehavior
    -0.83
    FieldBuilder
    -0.79
    .")
    
    -0.77
    ArgsConstructor
    -0.75
     numberWith
    -0.73
    HtmlAttribute
    -0.71
    ^(@)
    -0.71
    Portail
    -0.70
    extAlignment
    -0.68
    )");
    
    -0.68
    POSITIVE LOGITS
    正在
    0.57
     [
    0.56
    ']>
    0.54
     ...
    0.49
     <
    0.47
    <
    0.47
     detected
    0.47
     skipping
    0.47
    </code>
    0.46
    [
    0.45
    Activations Density 1.192%

    No Known Activations