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. 6370
    Prev
    Next
    INDEX
    Explanations

    attends to the token "of" from the corresponding token "the"

    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
    0:0.08
    1:0.09
    2:0.09
    3:0.11
    4:0.11
    5:0.10
    6:0.18
    7:0.21
    Negative Logits
    SharedDtor
    -0.42
    verwijspagina
    -0.35
    queryInterface
    -0.31
     getItemId
    -0.31
    APORE
    -0.30
    دانشنامهٔ
    -0.30
    ⓧ
    -0.29
    ineno
    -0.28
    ResumeLayout
    -0.28
    uitable
    -0.28
    POSITIVE LOGITS
    tôi
    0.32
    amaño
    0.31
    umenical
    0.29
     AssemblyTitle
    0.27
    ειτουργ
    0.27
    rabi
    0.26
     Gaylord
    0.26
     gawas
    0.25
     Walpole
    0.25
    ignements
    0.25
    Activations Density 0.241%

    No Known Activations