© 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. 12915
    Prev
    Next
    INDEX
    Explanations

    elements and attributes in a code or markup language structure, especially those related to styling and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    featureID
    -0.74
     otomatig
    -0.72
     مرئيه
    -0.68
    SharedCtor
    -0.62
    TagMode
    -0.62
    migrationBuilder
    -0.62
    QMetaType
    -0.59
    EndContext
    -0.59
    RegressionTest
    -0.58
    jspb
    -0.58
    POSITIVE LOGITS
     color
    0.39
    color
    0.36
     colors
    0.34
    Color
    0.33
    Render
    0.32
     Color
    0.32
    色
    0.31
    fär
    0.31
     render
    0.30
    分け
    0.29
    Activations Density 0.201%

    No Known Activations