Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9091
    Prev
    Next
    INDEX
    Explanations

    CSS and styling-related components in code snippets

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

    Code-related terms like "class" and "style"

    np_acts-logits-general · gemini-2.0-flash

    css classes and styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.83
     Anfitrión
    -0.72
     EconPapers
    -0.72
    AndEndTag
    -0.71
     Himo
    -0.68
    hyrchwyd
    -0.66
     kaynağından
    -0.66
    ThroughAttribute
    -0.65
    Herzliche
    -0.63
    )");
    
    -0.62
    POSITIVE LOGITS
    classnames
    0.85
     useStyles
    0.58
    styleUrls
    0.54
    toggleClass
    0.52
     makeStyles
    0.51
    styles
    0.48
    classList
    0.48
    classname
    0.46
     styling
    0.46
     css
    0.46
    Activations Density 0.050%

    No Known Activations