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. 1275
    Prev
    Next
    INDEX
    Explanations

    attends to empty array declarations from other declarations or statements

    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
    0:0.05
    1:0.05
    2:0.00
    3:0.01
    4:0.01
    5:0.02
    6:0.04
    7:0.03
    8:0.34
    9:0.19
    10:0.07
    11:0.03
    12:0.03
    13:0.02
    14:0.01
    15:0.03
    Negative Logits
    
    -0.66
    ſſung
    -0.65
    𓇠
    -0.65
    ſicht
    -0.64
    
    -0.63
    <unused43>
    -0.63
    <unused8>
    -0.63
    𓆱
    -0.63
    <unused3>
    -0.63
    <pad>
    -0.63
    POSITIVE LOGITS
     financiera
    0.11
     contratación
    0.10
     finanzas
    0.09
     intervenciones
    0.09
     intervención
    0.09
     financeira
    0.09
     financiación
    0.09
     dziecka
    0.09
     conducción
    0.09
     comprensión
    0.09
    Activations Density 0.483%

    No Known Activations