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. 1189
    Prev
    Next
    INDEX
    Explanations

    attends to non-empty numeric values from preceding empty token markers

    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
    0:0.03
    1:0.04
    2:0.01
    3:0.03
    4:0.02
    5:0.02
    6:0.04
    7:0.04
    8:0.42
    9:0.07
    10:0.05
    11:0.02
    12:0.02
    13:0.02
    14:0.01
    15:0.07
    Negative Logits
    
    -0.34
    ⩖
    -0.33
    SourceChecksum
    -0.33
    Personensuche
    -0.32
    ロウィン
    -0.32
     Bim
    -0.31
    
    -0.31
    TagHelper
    -0.31
    endphp
    -0.31
    gae
    -0.31
    POSITIVE LOGITS
     aislado
    0.18
     extranjero
    0.17
     fotográfica
    0.17
     prohibido
    0.17
     contemporáneo
    0.16
     plateado
    0.16
     literario
    0.16
     Moscú
    0.16
     mío
    0.16
     Infór
    0.16
    Activations Density 0.488%

    No Known Activations