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. 311
    Prev
    Next
    INDEX
    Explanations

    attends to championship-related tokens from tournament-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
    1:0.04
    2:0.52
    3:0.10
    4:0.05
    5:0.08
    6:0.06
    7:0.09
    Negative Logits
    MessageTagHelper
    -0.39
    fortawesome
    -0.36
    "):
    
    -0.35
    fjspx
    -0.35
    !")
    
    -0.34
    ...',
    -0.34
    WireFormatLite
    -0.34
    "},
    
    -0.34
     '',
    
    -0.33
    ',
    
    
    -0.33
    POSITIVE LOGITS
     These
    0.26
    みる
    0.25
      
    0.24
     That
    0.23
    ubscribe
    0.22
    atguigu
    0.22
    czenie
    0.21
    ↵↵
    0.21
     So
    0.21
    ferous
    0.20
    Activations Density 1.259%

    No Known Activations