© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102175
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structural components in text, especially related to code or script-like elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Structural elements in different text formats, including empty lines, closing parentheses after organizations, answer markers in Q&A formats, user identifiers in chat logs, and UI text elements in localization strings.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    stylers
    -0.69
    writeFieldEnd
    -0.65
    parsedMessage
    -0.64
     queſta
    -0.63
     OFDb
    -0.62
    Демографія
    -0.58
    новништво
    -0.58
    Geplaatst
    -0.56
    @[+][
    -0.56
     *++
    -0.56
    POSITIVE LOGITS
    ViewFeatures
    0.50
     intptr
    0.40
    is
    0.38
    <code>
    0.38
      
    0.37
                 
    0.35
        
    0.34
    „
    0.34
    “
    0.34
                
    0.33
    Activations Density 0.001%

    No Known Activations