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. 180
    Prev
    Next
    INDEX
    Explanations

    attends to semicolon tokens from closing bracket 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
    0:0.19
    1:0.14
    2:0.07
    3:0.03
    4:0.20
    5:0.22
    6:0.06
    7:0.05
    Negative Logits
    esterday
    -0.67
    UserScript
    -0.65
     समीक्षक
    -0.65
     المعيارى
    -0.65
    setVerticalGroup
    -0.59
    ^(@)
    -0.59
    BibitemShut
    -0.58
    دانشنامهٔ
    -0.58
     myſelf
    -0.57
     propOrder
    -0.57
    POSITIVE LOGITS
    ,
    0.85
    (
    0.56
    [
    0.50
    ?
    0.49
    .
    0.49
    ;
    0.47
    <
    0.47
    ,
    0.44
    :
    0.42
    、
    0.41
    Activations Density 0.135%

    No Known Activations