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-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 81
    Prev
    Next
    INDEX
    Explanations

    attends to Dutch-related tokens from Norwegian-related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 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
    1:0.03
    2:0.05
    3:0.19
    4:0.04
    5:0.05
    6:0.52
    7:0.08
    Negative Logits
    ↵↵
    -0.54
    <eos>
    -0.52
    ↵↵↵↵
    -0.49
    :✨
    -0.44
      
    -0.43
    ↵↵↵
    -0.42
     propOrder
    -0.42
       
    -0.41
    ThroughAttribute
    -0.38
    DoubleQuotes
    -0.37
    POSITIVE LOGITS
     myſelf
    0.52
     Efq
    0.52
     whoſe
    0.50
     $_"
    0.49
    neſs
    0.49
    ."</
    0.48
     }}$}
    0.48
    ſelves
    0.47
     Forumite
    0.47
     leaſt
    0.47
    Activations Density 0.000%

    No Known Activations