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. 6059
    Prev
    Next
    INDEX
    Explanations

    attends to numeric tokens from adjacent tokens that are empty brackets

    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
    0:0.03
    1:0.02
    2:0.02
    3:0.02
    4:0.82
    5:0.04
    6:0.01
    7:0.01
    Negative Logits
     
    -0.56
    '],
    
    -0.48
    '):
    
    -0.46
    ’).
    -0.41
    ']);
    
    -0.41
    )}^{
    -0.41
    '},
    
    -0.40
    <b>
    -0.40
     million
    -0.39
    )».
    -0.38
    POSITIVE LOGITS
     ExecuteAsync
    0.67
    省市镇
    0.61
    Identyfik
    0.56
    MemoryWarning
    0.52
    setVerticalGroup
    0.52
     المعيارى
    0.52
    RefNanny
    0.50
     дописавши
    0.50
    ViewFeatures
    0.49
    WebVitals
    0.49
    Activations Density 6.269%

    No Known Activations