© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7860
    Prev
    Next
    INDEX
    Explanations

    references to style, particularly in the context of design, fashion, or aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.70
    RepeatedField
    -0.68
    AddTagHelper
    -0.63
    PreExecute
    -0.63
    RegistryLite
    -0.63
     Audiodateien
    -0.61
     للمعارف
    -0.61
    HStack
    -0.61
    IBarButtonItem
    -0.60
    binar
    -0.60
    POSITIVE LOGITS
     style
    3.99
     Style
    3.96
    Style
    3.71
     STYLE
    3.66
    style
    3.53
     styles
    3.37
    STYLE
    3.29
     Styles
    3.13
     styled
    2.93
    Styles
    2.83
    Activations Density 0.061%

    No Known Activations