© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101955
    Prev
    Next
    INDEX
    Explanations

    mentions of CSS and its related properties or functions

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

    css declarations

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    from
    -0.46
    ParallelGroup
    -0.43
    hline
    -0.43
    ̷
    -0.43
    (
    -0.43
     foramen
    -0.42
    frontmatter
    -0.42
     useNavigate
    -0.41
     grantor
    -0.41
     doesn
    -0.41
    POSITIVE LOGITS
    css
    1.30
     css
    1.26
     CSS
    1.26
    Css
    1.25
    CSS
    1.23
     Css
    1.13
     CCS
    0.63
    postcss
    0.60
    dns
    0.59
    setStyleSheet
    0.59
    Activations Density 0.005%

    No Known Activations