© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3701
    Prev
    Next
    INDEX
    Explanations

    CSS styling attributes related to text formatting and layout

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    font styles and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Negative Logits
    Font
    -1.01
    font
    -0.95
    Fonts
    -0.89
     font
    -0.85
     fonts
    -0.84
    setFont
    -0.80
     Font
    -0.79
    fontSize
    -0.79
    FONT
    -0.78
    fonts
    -0.75
    POSITIVE LOGITS
     pleaſure
    0.81
     itſelf
    0.80
     Reverso
    0.76
     ſche
    0.76
     purpoſe
    0.76
    oredCriteria
    0.75
     raiſ
    0.72
     himſelf
    0.70
     Theſe
    0.70
     ſte
    0.69
    Activations Density 0.010%

    No Known Activations