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. 5807
    Prev
    Next
    INDEX
    Explanations

    attends to integer-related tokens from tokens related to lists or arrays

    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
    0:0.05
    1:0.11
    2:0.07
    3:0.04
    4:0.12
    5:0.47
    6:0.04
    7:0.06
    Negative Logits
    AnchorStyles
    -0.44
    IsContent
    -0.36
    AddHtmlAttribute
    -0.34
    initializeApp
    -0.32
     '\\;'
    -0.31
    elemField
    -0.31
    figsize
    -0.30
    ScopeManager
    -0.30
    WriteTagHelper
    -0.30
    tagHelper
    -0.30
    POSITIVE LOGITS
    ArrowToggle
    0.28
    setH
    0.23
    rovna
    0.22
    нила
    0.21
     समीक्षाओं
    0.21
     sauvages
    0.20
    니메이션
    0.20
     Leto
    0.20
     malta
    0.20
    encias
    0.20
    Activations Density 0.256%

    No Known Activations