© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6716
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to font formatting and styles

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

    "font" and related styling

    np_acts-logits-general · gemini-2.0-flash

    font-variant and font-family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     vicenda
    -0.57
     FixedUpdate
    -0.57
    delwed
    -0.56
    ("/:
    -0.55
     Vrij
    -0.53
    {{/
    -0.51
    reality
    -0.50
    ⎨
    -0.50
    CloseOperation
    -0.50
    isReady
    -0.49
    POSITIVE LOGITS
    Font
    1.21
    font
    1.17
     font
    1.09
     Font
    1.08
    setFont
    1.01
     UIFont
    1.00
     FONT
    0.94
    FONT
    0.94
    Fonts
    0.93
    QFont
    0.91
    Activations Density 0.036%

    No Known Activations