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. 67
    Prev
    Next
    INDEX
    Explanations

    attends to Facebook-related tokens from 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
    0:0.07
    1:0.02
    2:0.03
    3:0.06
    4:0.49
    5:0.11
    6:0.07
    7:0.10
    Negative Logits
    UnitTesting
    -0.35
    avigation
    -0.31
     Conferences
    -0.31
     Mehdi
    -0.30
    y
    -0.30
     Casualty
    -0.30
     reverb
    -0.29
    TestTools
    -0.29
     Validators
    -0.29
     Leagues
    -0.29
    POSITIVE LOGITS
    "])
    
    0.49
    ")));
    
    0.47
     {}".
    0.45
    '));
    
    0.45
    "))
    
    0.43
    "));
    
    0.43
    }")
    
    0.41
    "),
    
    0.41
    "]);
    
    0.41
    IndentedString
    0.40
    Activations Density 0.017%

    No Known Activations