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. 332
    Prev
    Next
    INDEX
    Explanations

    attends to body-related tokens from clothing or other coverings 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
    0:0.01
    1:0.06
    2:0.50
    3:0.09
    4:0.05
    5:0.10
    6:0.05
    7:0.09
    Negative Logits
     myſelf
    -0.76
     itſelf
    -0.74
     Monfieur
    -0.71
     doubtnut
    -0.69
     Efq
    -0.68
     Theſe
    -0.67
     themſelves
    -0.66
     ―――――
    -0.65
     pleaſure
    -0.64
    ſelf
    -0.63
    POSITIVE LOGITS
    .
    0.45
     to
    0.35
    ,
    0.34
    -
    0.34
    <eos>
    0.34
     
    0.34
     U
    0.33
    /
    0.32
     (
    0.31
     O
    0.31
    Activations Density 1.128%

    No Known Activations