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. 8498
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation indicating equations, variables, and mathematical relationships

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

    Mathematical/scientific notation and symbols

    np_acts-logits-general · gemini-2.0-flash

    math notation and symbols

    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
    msub
    -0.53
     kal
    -0.50
    }_
    -0.49
    anna
    -0.47
    }}_
    -0.47
    entra
    -0.47
    ContentView
    -0.46
    det
    -0.46
    putAll
    -0.45
     Iden
    -0.45
    POSITIVE LOGITS
    ^{
    0.96
     ^{
    0.95
    }^{
    0.93
    <sup>
    0.92
    aarrggbb
    0.86
    bootstrapcdn
    0.82
    ^
    0.80
    ^[
    0.79
    AsUp
    0.77
     }^{
    0.77
    Activations Density 0.600%

    No Known Activations