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. 1256
    Prev
    Next
    INDEX
    Explanations

    attends to the closing parenthesis from arbitrary preceding tokens

    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
    0:0.06
    1:0.03
    2:0.01
    3:0.02
    4:0.03
    5:0.03
    6:0.02
    7:0.02
    8:0.45
    9:0.11
    10:0.03
    11:0.02
    12:0.02
    13:0.02
    14:0.01
    15:0.04
    Negative Logits
     desmotivaciones
    -0.77
     Económica
    -0.73
     asamblea
    -0.71
     Infór
    -0.70
     Sünde
    -0.69
     navideño
    -0.67
     Italij
    -0.67
     comunión
    -0.66
     Meksika
    -0.66
     feroit
    -0.66
    POSITIVE LOGITS
     st
    0.38
     cal
    0.36
     tri
    0.36
     cl
    0.36
     Co
    0.36
     ra
    0.35
     â
    0.35
     pl
    0.35
     mar
    0.35
    ib
    0.35
    Activations Density 0.514%

    No Known Activations