© 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. 20-GEMMASCOPE-RES-16K
    11. 15468
    Prev
    Next
    INDEX
    Explanations

    JSON object key-value pairs

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

    Code-related strings involving colons and quotation marks

    np_acts-logits-general · gemini-2.0-flash

    JSON schema structure

    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
    ;
    -0.68
     clearColor
    -0.59
     Huns
    -0.56
    oo
    -0.54
     sofá
    -0.51
     AFS
    -0.51
    ↵↵
    -0.50
     CGPoint
    -0.49
    -0.49
     CGSize
    -0.49
    POSITIVE LOGITS
    TagMode
    0.97
     "",
    0.92
    migrationBuilder
    0.89
    XmlAccessorType
    0.89
     AssemblyTitle
    0.89
    $',
    0.89
    */,
    0.88
    $",
    0.86
    InjectAttribute
    0.84
     CreateTagHelper
    0.83
    Activations Density 0.272%
    No Known Activations