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. 39
    Prev
    Next
    INDEX
    Explanations

    attends to the token "uint" from related code tokens, specifically focusing on data types and function arguments

    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
    1:0.02
    2:0.05
    3:0.38
    4:0.05
    5:0.06
    6:0.33
    7:0.05
    Negative Logits
     myſelf
    -1.41
     itſelf
    -1.39
     pleaſure
    -1.37
     Efq
    -1.27
     purpoſe
    -1.24
     raiſ
    -1.23
     Theſe
    -1.23
     Jefus
    -1.21
     ſche
    -1.20
     Majefty
    -1.20
    POSITIVE LOGITS
    <eos>
    0.73
    ,
    0.69
    ↵
    0.68
    .
    0.68
     
    0.58
     I
    0.57
     (
    0.55
    ...
    0.51
     of
    0.50
     to
    0.50
    Activations Density 0.206%

    No Known Activations