Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6530
    Prev
    Next
    INDEX
    Explanations

    attends to the specific tokens "Gators," "Fordham," "Eagles," and "Blues" from their respective team or organization tokens indicated later

    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
    0:0.36
    1:0.19
    2:0.14
    3:0.06
    4:0.05
    5:0.03
    6:0.06
    7:0.07
    Negative Logits
    sizeCache
    -0.24
    WireFormat
    -0.23
    [--
    -0.21
    eqn
    -0.20
    ัญ
    -0.20
    ẽ
    -0.20
    addPreferredGap
    -0.20
     pince
    -0.20
    Adds
    -0.20
    Migrations
    -0.19
    POSITIVE LOGITS
     AssemblyTitle
    0.31
    AutoresizingMask
    0.27
     متعلقه
    0.26
    Παραπομπές
    0.26
    expandindo
    0.25
    ArrowToggle
    0.25
     initComponents
    0.25
    Билгалдахарш
    0.24
     Catawiki
    0.23
     Wikimédia
    0.23
    Activations Density 0.358%

    No Known Activations