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. 5558
    Prev
    Next
    INDEX
    Explanations

    attends to the values marked with double asterisks from numerical values marked with double brackets

    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
    0:0.07
    1:0.14
    2:0.06
    3:0.06
    4:0.18
    5:0.28
    6:0.07
    7:0.11
    Negative Logits
    ValueStyle
    -0.33
    췄
    -0.31
     незавершена
    -0.31
     Pelt
    -0.31
    zzlies
    -0.31
    AddTagHelper
    -0.31
    GIVEREF
    -0.31
    SBATCH
    -0.31
    ilitation
    -0.30
    aronder
    -0.29
    POSITIVE LOGITS
    RenderAtEndOf
    0.40
     francese
    0.30
     Франции
    0.29
    bhan
    0.29
    بوب
    0.29
    multer
    0.29
     françaises
    0.28
    toise
    0.28
     penna
    0.28
     StatelessWidget
    0.28
    Activations Density 1.310%

    No Known Activations