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. 1190
    Prev
    Next
    INDEX
    Explanations

    attends to specific character sequences or patterns from earlier tokens in the sequence

    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
    0:0.08
    1:0.02
    2:0.01
    3:0.02
    4:0.02
    5:0.03
    6:0.03
    7:0.03
    8:0.11
    9:0.13
    10:0.07
    11:0.24
    12:0.05
    13:0.04
    14:0.01
    15:0.02
    Negative Logits
     HF
    -0.88
    
    -0.87
     SES
    -0.85
     NAP
    -0.85
     GG
    -0.85
     KL
    -0.85
     Fli
    -0.84
     MG
    -0.84
     Alf
    -0.84
     HT
    -0.84
    POSITIVE LOGITS
     zijne
    0.65
     Italij
    0.62
     čierna
    0.60
     oídos
    0.60
     almohada
    0.56
     rodillas
    0.56
     istrinya
    0.56
     mijne
    0.55
     rumahnya
    0.55
     burbujas
    0.54
    Activations Density 0.006%

    No Known Activations