© 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 EvalsExportsinterp-engineNEWAPI 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. 105483
    Prev
    Next
    INDEX
    Explanations

    instances of formatting or code structures within programming or data representations

    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
     JpaRepository
    -0.77
    +#+#
    -0.74
     propOrder
    -0.73
     Autorizaciones
    -0.69
    MessageTagHelper
    -0.69
    writeFieldEnd
    -0.66
     arşivlendi
    -0.66
    
    -0.66
     الاطلاع
    -0.66
    localctx
    -0.65
    POSITIVE LOGITS
    Classic
    0.48
    Stream
    0.46
    Global
    0.45
    Hidden
    0.45
    Clinical
    0.44
    Code
    0.43
    Script
    0.42
    Static
    0.42
    Description
    0.41
    Package
    0.41
    Activations Density 0.005%

    No Known Activations