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. 1225
    Prev
    Next
    INDEX
    Explanations

    attends to closing statements or braces from preceding code elements

    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
    0:0.01
    1:0.01
    2:0.01
    3:0.02
    4:0.01
    5:0.01
    6:0.06
    7:0.03
    8:0.06
    9:0.07
    10:0.02
    11:0.01
    12:0.02
    13:0.47
    14:0.07
    15:0.05
    Negative Logits
    -0.32
    ↵
    -0.32
    }
    
    -0.30
     
    
    -0.28
    :
    
    -0.27
    $
    
    -0.26
    '>
    
    -0.26
    "]
    
    -0.25
     />
    
    -0.25
    {
    
    -0.25
    POSITIVE LOGITS
     Paglinawan
    0.55
    :✨
    0.52
    TagMode
    0.48
     ویکی‌پدی
    0.47
    Autoritní
    0.47
    uxxxx
    0.47
    awtextra
    0.47
     autorytatywna
    0.46
     noDo
    0.45
     témoig
    0.45
    Activations Density 0.112%

    No Known Activations