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-2-2B
    4. Attention Out - 16k
    5. 10-GEMMASCOPE-ATT-16K
    6. 6181
    Prev
    Next
    INDEX
    Explanations

    attends to context-specific terms from corresponding tokens that represent categories 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
    1:0.14
    2:0.15
    3:0.08
    4:0.10
    5:0.04
    6:0.16
    7:0.14
    Negative Logits
     MonoBehaviour
    -0.35
    RenderAtEndOf
    -0.27
     externes
    -0.26
    endpush
    -0.24
    rijfs
    -0.24
    肇
    -0.23
    Linq
    -0.23
    aarrggbb
    -0.23
     vernünf
    -0.23
    GEBURTSDATUM
    -0.23
    POSITIVE LOGITS
     USDA
    0.30
     Radon
    0.30
     препратки
    0.30
     Sma
    0.29
     numberWith
    0.29
    Autoritní
    0.29
    apunov
    0.29
     Minato
    0.29
     Vard
    0.29
    AutoScaleMode
    0.29
    Activations Density 0.000%

    No Known Activations