© 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. 22-GEMMASCOPE-RES-16K
    11. 11400
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and curly braces in code formatting

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

    Code snippets with brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing brace or parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.87
    MigrationBuilder
    -0.51
    aller
    -0.50
     var
    -0.48
     Bed
    -0.48
     kons
    -0.48
    :['
    -0.47
    bed
    -0.47
     Rub
    -0.46
    [
    -0.46
    POSITIVE LOGITS
     comunista
    0.66
     noires
    0.66
     fenó
    0.66
     actuels
    0.64
    pidou
    0.63
     malignancy
    0.62
     teórico
    0.62
     étrang
    0.62
     exemplaires
    0.62
     récents
    0.61
    Activations Density 0.222%

    No Known Activations