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. 1257
    Prev
    Next
    INDEX
    Explanations

    attends to mathematical terms related to norms from terms related to bounds

    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
    0:0.00
    1:0.01
    2:0.24
    3:0.18
    4:0.01
    5:0.01
    6:0.05
    7:0.03
    8:0.01
    9:0.03
    10:0.01
    11:0.01
    12:0.01
    13:0.05
    14:0.26
    15:0.01
    Negative Logits
     mijne
    -0.89
     zijne
    -0.89
    zelfde
    -0.74
     Económica
    -0.73
     Infór
    -0.72
     ciudadana
    -0.70
     Italij
    -0.69
     miniaturka
    -0.68
     vrijwilli
    -0.68
     natuurlijke
    -0.67
    POSITIVE LOGITS
     a
    0.57
     car
    0.55
     box
    0.53
     file
    0.53
     tr
    0.53
     log
    0.52
     eff
    0.52
     in
    0.52
     bus
    0.52
     tran
    0.52
    Activations Density 0.084%

    No Known Activations