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. 10-GEMMASCOPE-ATT-16K
    6. 6263
    Prev
    Next
    INDEX
    Explanations

    attends to action-related tokens from specific token types

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.11
    1:0.10
    2:0.49
    3:0.04
    4:0.04
    5:0.04
    6:0.04
    7:0.08
    Negative Logits
     Buddy
    -0.29
    gapi
    -0.29
    ClientRect
    -0.28
    Kinematic
    -0.27
     f
    -0.26
    قتل
    -0.26
     כן
    -0.26
    .​
    -0.25
    owice
    -0.25
    ssin
    -0.25
    POSITIVE LOGITS
    adaptiveStyles
    0.44
     ExecuteAsync
    0.43
    endphp
    0.43
     للمعارف
    0.42
    UnusedPrivate
    0.42
     Paglinawan
    0.41
    bootstrapcdn
    0.40
     yyr
    0.40
     مرئيه
    0.38
    клопе
    0.38
    Activations Density 0.186%

    No Known Activations