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. 5965
    Prev
    Next
    INDEX
    Explanations

    attends to numeric tokens from tokens containing slashes or other specific formatting

    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
    1:0.10
    2:0.07
    3:0.05
    4:0.05
    5:0.04
    6:0.45
    7:0.13
    Negative Logits
    queryInterface
    -0.45
    mbggenerated
    -0.36
    izophren
    -0.35
     Shimizu
    -0.34
    ̣ng
    -0.33
    therlands
    -0.33
    DFT
    -0.33
     बजाय
    -0.33
    Goodreads
    -0.33
    WRP
    -0.33
    POSITIVE LOGITS
    Autoritní
    0.50
     Waray
    0.45
    WithIOException
    0.43
    ReusableCell
    0.42
    Искәрмәләр
    0.41
    Kanpo
    0.40
    Билгалдахарш
    0.40
     InputDecoration
    0.40
    tagHelperRunner
    0.39
    رشف
    0.39
    Activations Density 0.044%

    No Known Activations