© 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. 1-GEMMASCOPE-RES-16K
    11. 5841
    Prev
    Next
    INDEX
    Explanations

    references to scoring metrics or assessments in the context of evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.96
     ویکی‌پدی
    -0.89
    IUrlHelper
    -0.78
    UpInside
    -0.74
    Geplaatst
    -0.74
    migrationBuilder
    -0.74
    دانشنامهٔ
    -0.68
    LookAnd
    -0.68
    IGraphics
    -0.67
    ništ
    -0.67
    POSITIVE LOGITS
     readings
    0.95
     reading
    0.86
    reading
    0.85
    Score
    0.80
     victory
    0.76
     score
    0.73
     Score
    0.72
     Readings
    0.71
    score
    0.71
    READ
    0.69
    Activations Density 0.078%

    No Known Activations