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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 10609
    Prev
    Next
    INDEX
    Explanations

    tokens related to data serialization and API response structures

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

    code constants like `SIG`, `SOCK`, `SOL`, `CLOCK`, `NOTE`, `PT`, `S_`, `IFF_`, `Category:`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    complexContent
    -0.60
    parsedMessage
    -0.59
    OGND
    -0.59
    queryInterface
    -0.57
    matchCondition
    -0.55
    存于互联网档案馆
    -0.54
    ArgumentParser
    -0.52
    msgTypes
    -0.52
    %)$
    -0.50
    RenderAtEndOf
    -0.49
    POSITIVE LOGITS
    principalTable
    0.47
    lancer
    0.44
    พัน
    0.41
     privées
    0.41
    expliquer
    0.38
    ように
    0.37
     spreken
    0.37
    correre
    0.37
    ômetro
    0.36
     sama
    0.36
    Activations Density 0.287%

    No Known Activations