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. 1370
    Prev
    Next
    INDEX
    Explanations

    attends to programming or technical terms from related Java or coding concepts

    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
    0:0.10
    1:0.05
    2:0.01
    3:0.02
    4:0.01
    5:0.02
    6:0.05
    7:0.05
    8:0.08
    9:0.17
    10:0.15
    11:0.10
    12:0.04
    13:0.03
    14:0.02
    15:0.03
    Negative Logits
     plufieurs
    -0.81
     desmotivaciones
    -0.79
     zijne
    -0.76
     Económica
    -0.76
     feroit
    -0.74
     Wikiseite
    -0.74
     avoient
    -0.73
     ainfi
    -0.73
     čierna
    -0.73
     étoient
    -0.73
    POSITIVE LOGITS
     a
    0.59
     the
    0.52
     and
    0.50
     \
    0.49
     G
    0.48
    /
    0.48
     for
    0.47
     sh
    0.47
     Sel
    0.46
    ↵
    0.46
    Activations Density 0.006%

    No Known Activations