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. 1353
    Prev
    Next
    INDEX
    Explanations

    attends to various corporate and organizational entities from related tokens indicating roles or features associated with those entities

    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
    1:0.02
    2:0.04
    3:0.03
    4:0.01
    5:0.02
    6:0.03
    7:0.09
    8:0.02
    9:0.02
    10:0.01
    11:0.01
    12:0.02
    13:0.45
    14:0.09
    15:0.03
    Negative Logits
     extranjera
    -0.60
     katholischen
    -0.57
     Flüssigkeit
    -0.57
     negociación
    -0.57
     antigüedad
    -0.56
     Unterscheidung
    -0.55
     disposiciones
    -0.55
     cooperación
    -0.55
     Menschheit
    -0.55
     Italij
    -0.54
    POSITIVE LOGITS
     Card
    0.94
     Pool
    0.90
     Tool
    0.90
     Mail
    0.89
     Story
    0.89
     Board
    0.89
     Line
    0.88
     Seed
    0.88
     Grid
    0.88
     Chart
    0.88
    Activations Density 0.733%

    No Known Activations