© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 81826
    Prev
    Next
    INDEX
    Explanations

    references to the Windows operating system and related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ⓧ
    -1.05
    yarnpkg
    -0.69
    Tembelea
    -0.67
    tagHelperRunner
    -0.67
    RegressionTest
    -0.66
    writeFieldEnd
    -0.66
     disambiguazione
    -0.65
    parsedMessage
    -0.64
     transfieras
    -0.64
     مرئيه
    -0.63
    POSITIVE LOGITS
    Windows
    0.88
    windows
    0.73
     Windows
    0.73
     windows
    0.59
    WINDOWS
    0.52
    window
    0.50
    Window
    0.50
     WINDOWS
    0.45
     window
    0.43
    窗
    0.43
    Activations Density 0.001%

    No Known Activations