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. 1194
    Prev
    Next
    INDEX
    Explanations

    attends to the token "javax" from various programming-related 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
    0:0.02
    1:0.02
    2:0.02
    3:0.12
    4:0.13
    5:0.01
    6:0.02
    7:0.03
    8:0.01
    9:0.01
    10:0.02
    11:0.38
    12:0.04
    13:0.04
    14:0.03
    15:0.01
    Negative Logits
     zijne
    -0.62
    ſelf
    -0.62
     $_"
    -0.61
    parsedMessage
    -0.61
     étoit
    -0.57
     étoient
    -0.56
     $_(
    -0.55
     ainfi
    -0.55
     avoient
    -0.54
     feroit
    -0.54
    POSITIVE LOGITS
     in
    0.52
     
    0.50
      
    0.50
     (
    0.50
     time
    0.49
     that
    0.49
     new
    0.49
     to
    0.49
     name
    0.49
     and
    0.48
    Activations Density 0.005%

    No Known Activations