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. 119
    Prev
    Next
    INDEX
    Explanations

    attends to tokens related to library or resource identifiers from tokens that specify groups

    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
    1:0.03
    2:0.07
    3:0.33
    4:0.14
    5:0.09
    6:0.17
    7:0.11
    Negative Logits
     myſelf
    -0.60
    etheless
    -0.60
    NUMX
    -0.57
     Efq
    -0.56
     itſelf
    -0.55
    ſelf
    -0.53
    ſelves
    -0.53
    esterday
    -0.53
     StatelessWidget
    -0.51
    ighed
    -0.50
    POSITIVE LOGITS
    .
    0.44
    -
    0.38
    ”
    0.37
    ,
    0.34
     [
    0.34
     &
    0.33
     -
    0.33
    /
    0.33
    li
    0.33
    ”.
    0.33
    Activations Density 0.001%

    No Known Activations