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. 5853
    Prev
    Next
    INDEX
    Explanations

    attends to specific tokens related to mathematical operations from tokens discussing list or array elements

    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
    0:0.17
    1:0.21
    2:0.08
    3:0.09
    4:0.10
    5:0.11
    6:0.12
    7:0.09
    Negative Logits
     ویکی‌پدیا
    -0.42
    ContentAsync
    -0.42
     lenker
    -0.39
     gyhoeddwyd
    -0.38
     bağlantılar
    -0.38
    IsContent
    -0.36
    DeleteBehavior
    -0.35
    MessageOf
    -0.34
     دیکھیے
    -0.33
     Вікіпе
    -0.33
    POSITIVE LOGITS
    commodations
    0.34
    CAPT
    0.34
    bcryptjs
    0.33
    nero
    0.33
    GEBURTS
    0.33
    {(-
    0.31
     Efq
    0.31
     leva
    0.31
     quedado
    0.30
    hera
    0.30
    Activations Density 0.073%

    No Known Activations