© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103986
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    SPATH
    -0.57
    CardHeader
    -0.57
    AddTagHelper
    -0.52
    RenderAtEndOf
    -0.52
    GEBURTSDATUM
    -0.48
    invokeLater
    -0.47
     ModelExpression
    -0.45
    classnames
    -0.44
    enderror
    -0.44
    UseVisualStyle
    -0.43
    POSITIVE LOGITS
     solaire
    0.49
    SharedCtor
    0.46
    principalColumn
    0.46
     հղումներ
    0.42
    zeera
    0.41
    Personensuche
    0.41
     bidet
    0.40
    rscheinlich
    0.39
    ouvrage
    0.38
     bankası
    0.38
    Activations Density 0.027%

    No Known Activations