© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1626
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their associated attributes

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

    CSS stylesheets and styling

    np_acts-logits-general · gemini-2.0-flash

    css styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.76
    fromCharCode
    -0.73
     hObject
    -0.70
     ویکی‌پدیا
    -0.67
     publicitaires
    -0.66
     propOrder
    -0.66
     magique
    -0.65
     américains
    -0.65
    GEBURTS
    -0.62
     financières
    -0.62
    POSITIVE LOGITS
     style
    1.27
     styles
    1.19
     styling
    1.16
    style
    1.08
    css
    1.05
     Styles
    1.04
     Style
    1.04
    styles
    1.02
     css
    0.99
    Style
    0.99
    Activations Density 0.078%

    No Known Activations