Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Attention Out - 16k
    5. 10-GEMMASCOPE-ATT-16K
    6. 6469
    Prev
    Next
    INDEX
    Explanations

    attends to numerical results or statistical terms from corresponding numerical references or identifiers

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.15
    1:0.12
    2:0.09
    3:0.11
    4:0.08
    5:0.09
    6:0.06
    7:0.25
    Negative Logits
     ddelweddau
    -0.39
     Gwyn
    -0.33
    thâu
    -0.32
    はじめに
    -0.32
     ويكيميديا
    -0.31
    ympto
    -0.31
     esternos
    -0.31
     Euphrates
    -0.30
    glEnd
    -0.30
     Sputnik
    -0.30
    POSITIVE LOGITS
    expandindo
    0.28
    Datuak
    0.27
    節
    0.27
    higan
    0.27
     âgées
    0.26
    ETRY
    0.26
    SharedCtor
    0.26
    illet
    0.26
     berk
    0.25
    dée
    0.25
    Activations Density 0.176%

    No Known Activations