© 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. 104355
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or paragraphs in a document, indicated by formatting tokens

    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
    principalColumn
    -0.50
    ArgsConstructor
    -0.47
     Losing
    -0.47
     replay
    -0.46
    onsor
    -0.46
     ब्रेकडाउन
    -0.45
    AddHtmlAttribute
    -0.44
    defe
    -0.44
     Paglinawan
    -0.43
     ModelExpression
    -0.43
    POSITIVE LOGITS
    #+#
    0.42
    front
    0.41
    basicConfig
    0.41
    Dichloropropene
    0.40
     RoutedEventArgs
    0.38
     metra
    0.37
    cstdio
    0.37
    Changed
    0.36
    chandra
    0.36
     شرح
    0.35
    Activations Density 0.005%

    No Known Activations