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. 1339
    Prev
    Next
    INDEX
    Explanations

    attends to the keyword "Name" from identifiers or elements that reflect abstract concepts reflected in the code

    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
    0:0.02
    1:0.03
    2:0.01
    3:0.08
    4:0.51
    5:0.02
    6:0.02
    7:0.02
    8:0.01
    9:0.02
    10:0.02
    11:0.02
    12:0.09
    13:0.02
    14:0.01
    15:0.01
    Negative Logits
     Moscú
    -0.54
     perfección
    -0.52
     plateado
    -0.52
     Italij
    -0.51
     Infór
    -0.51
     importación
    -0.49
     mecánico
    -0.48
     civilización
    -0.48
     ciudadanía
    -0.48
     actualidad
    -0.48
    POSITIVE LOGITS
     PTS
    0.64
     QT
    0.63
     Repo
    0.63
     Pho
    0.62
     PTT
    0.61
     NPS
    0.61
     Hex
    0.61
     GIT
    0.60
     Jet
    0.60
     SF
    0.60
    Activations Density 0.044%

    No Known Activations