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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 166
    Prev
    Next
    INDEX
    Explanations

    attends to CSS-related tokens from HTML or JavaScript-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    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

    Head Attr Weights
    0:0.03
    1:0.04
    2:0.10
    3:0.34
    4:0.10
    5:0.13
    6:0.13
    7:0.11
    Negative Logits
    .
    -0.62
    -
    -0.61
    (
    -0.59
    /
    -0.59
    S
    -0.59
    \
    -0.57
    D
    -0.56
    $
    -0.54
     
    -0.54
    M
    -0.54
    POSITIVE LOGITS
    NUMX
    1.11
    ^(@)
    1.04
    "])
    
    1.02
    etheless
    1.02
     Мексичка
    1.01
     myſelf
    1.00
    DockStyle
    0.99
    berdayakan
    0.99
    BibitemShut
    0.99
     itſelf
    0.98
    Activations Density 0.001%

    No Known Activations