© 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-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9667
    Prev
    Next
    INDEX
    Explanations

    CSS and layout-related properties in web design or mobile development content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     straff
    -0.31
    RequestMapping
    -0.30
    Rim
    -0.29
     Rim
    -0.29
    cur
    -0.28
     against
    -0.27
     détach
    -0.27
    pa
    -0.27
    Fld
    -0.27
    dire
    -0.27
    POSITIVE LOGITS
    setVerticalGroup
    0.85
    AnchorStyles
    0.73
    tagHelperRunner
    0.70
     height
    0.65
     ModelExpression
    0.63
    height
    0.62
    providedIn
    0.62
    تقاوى
    0.61
    innerHeight
    0.61
    ConstraintMaker
    0.61
    Activations Density 0.126%

    No Known Activations