© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 591
    Prev
    Next
    INDEX
    Explanations

    statistical terms and concepts related to efficiency and estimation

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

    numerical values and their specific formatting within academic or statistical contexts

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

    numbers following or preceding certain tokens

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ModelExpression
    -0.90
    BASELINE
    -0.72
     surla
    -0.70
     isInitialized
    -0.67
     Paglinawan
    -0.67
    MigrationBuilder
    -0.67
    AddHtmlAttribute
    -0.66
     HttpNotFound
    -0.65
     MenuView
    -0.64
    Rhestr
    -0.63
    POSITIVE LOGITS
     nearly
    0.44
    vány
    0.44
     impression
    0.43
    şme
    0.42
    hoben
    0.41
    4
    0.40
     Schot
    0.40
    PAGES
    0.39
     الحره
    0.39
     Zit
    0.38
    Activations Density 0.059%

    No Known Activations