© 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. 119919
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to biological functions and conditions

    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
    SharedDtor
    -0.61
     nonUne
    -0.53
     дописавши
    -0.53
    WithIOException
    -0.52
    RegressionTest
    -0.50
    DispatchToProps
    -0.49
    adaptiveStyles
    -0.49
    RenderAtEndOf
    -0.46
     '\\;'
    -0.46
    IsMutable
    -0.45
    POSITIVE LOGITS
    inSlope
    0.38
    ChildScrollView
    0.36
    setVerticalGroup
    0.34
     gaz
    0.33
     xoay
    0.33
    writerow
    0.32
    ticulate
    0.32
    StructField
    0.31
    dis
    0.31
    seck
    0.31
    Activations Density 0.146%

    No Known Activations