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. 5954
    Prev
    Next
    INDEX
    Explanations

    attends to the pronoun "who" or "that" from related tokens "have," "of," or their associated numerals

    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
    0:0.18
    1:0.17
    2:0.19
    3:0.04
    4:0.03
    5:0.02
    6:0.04
    7:0.29
    Negative Logits
     vů
    -0.29
    ことにしました
    -0.28
     sauvages
    -0.28
     supérieurs
    -0.28
    douard
    -0.27
     direttore
    -0.27
     politique
    -0.26
    étape
    -0.26
    確認ください
    -0.26
     stället
    -0.26
    POSITIVE LOGITS
    StoryboardSegue
    0.40
    AddHtmlAttribute
    0.29
    ulaski
    0.28
     noqa
    0.28
    CloseOperation
    0.28
    MergeFrom
    0.27
     Мексичка
    0.27
    tomation
    0.27
     isNameExpr
    0.26
    paux
    0.26
    Activations Density 0.432%

    No Known Activations