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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5494
    Prev
    Next
    INDEX
    Explanations

    attends to numeric tokens from source code-related tokens

    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
    1:0.11
    2:0.14
    3:0.11
    4:0.10
    5:0.10
    6:0.11
    7:0.20
    Negative Logits
    GEBURTSDATUM
    -0.40
     برانيه
    -0.40
    aarrggbb
    -0.40
     itſelf
    -0.39
     myſelf
    -0.39
     externi
    -0.39
     fieldNum
    -0.37
     ویکی‌پدیا
    -0.37
    AccessorTable
    -0.37
    IBOutlet
    -0.37
    POSITIVE LOGITS
     médicale
    0.26
    かね
    0.24
     He
    0.22
    TTF
    0.22
    monium
    0.22
     guste
    0.22
     P
    0.22
    Audrey
    0.21
    ijão
    0.21
    phorbia
    0.20
    Activations Density 0.011%

    No Known Activations