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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1308
    Prev
    Next
    INDEX
    Explanations

    attends to the varying forms of "include" from different contexts related to additional elements or components

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.01
    1:0.01
    2:0.01
    3:0.01
    4:0.00
    5:0.02
    6:0.52
    7:0.11
    8:0.01
    9:0.00
    10:0.00
    11:0.01
    12:0.01
    13:0.08
    14:0.10
    15:0.03
    Negative Logits
    <unused43>
    -0.96
    <unused80>
    -0.96
    <unused17>
    -0.96
    <unused41>
    -0.96
    <unused14>
    -0.95
    <unused8>
    -0.95
    <unused16>
    -0.95
    <unused20>
    -0.95
    <pad>
    -0.95
    <unused3>
    -0.95
    POSITIVE LOGITS
     perfección
    0.28
     bahía
    0.23
     niebla
    0.23
     actualidad
    0.21
     Spuren
    0.20
     tambahan
    0.20
     antemano
    0.19
     oscuridad
    0.19
     juventud
    0.19
     orilla
    0.18
    Activations Density 0.448%

    No Known Activations