© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6483
    Prev
    Next
    INDEX
    Explanations

    references to external elements or comparisons in various contexts

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

    references to other research, groups, or research fields.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    intahan
    -0.63
     jspb
    -0.53
    setVerticalGroup
    -0.50
    migrationBuilder
    -0.50
     surla
    -0.49
     otomatig
    -0.45
    ंदीखरीदारी
    -0.45
    httphttps
    -0.44
    BSITE
    -0.43
    ulemon
    -0.43
    POSITIVE LOGITS
     other
    0.81
     andere
    0.78
     OTHER
    0.77
     autres
    0.74
    Other
    0.73
     otros
    0.73
     outros
    0.73
    其它
    0.72
     Other
    0.72
     otras
    0.72
    Activations Density 0.339%

    No Known Activations