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. 464
    Prev
    Next
    INDEX
    Explanations

    attends to the "@" symbol from tokens related to specific domains or descriptions

    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
    0:0.05
    1:0.04
    2:0.05
    3:0.17
    4:0.12
    5:0.05
    6:0.29
    7:0.19
    Negative Logits
    ↵↵↵
    -0.41
    verwijspagina
    -0.40
    ServletConfig
    -0.38
    ItemLayout
    -0.34
     Spéc
    -0.34
     venuto
    -0.33
    tison
    -0.32
    ↵↵↵↵
    -0.32
    RefNanny
    -0.31
     eléctricos
    -0.31
    POSITIVE LOGITS
    __':
    
    0.47
    EndInit
    0.41
    __":
    
    0.37
    )");
    
    0.36
    
    
    0.35
    BeginInit
    0.35
     Signalez
    0.35
    `,
    
    0.34
    __':
    0.34
    writerow
    0.34
    Activations Density 0.006%

    No Known Activations