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. 0-GEMMASCOPE-ATT-16K
    6. 220
    Prev
    Next
    INDEX
    Explanations

    attends to the token "Water" from related tokens that refer to specific contexts or entities like "gate," "mat," "bury," "street," and "fall."

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.54
    1:0.01
    2:0.02
    3:0.02
    4:0.22
    5:0.11
    6:0.01
    7:0.04
    Negative Logits
    AddTagHelper
    -0.45
    oa̍t
    -0.42
    enterOuterAlt
    -0.42
     merve
    -0.42
     engraçadas
    -0.41
     prêtres
    -0.41
    URLException
    -0.40
     defaultstate
    -0.40
     وتسجيلات
    -0.40
    SaveChangesAsync
    -0.40
    POSITIVE LOGITS
    ↵
    0.28
     
    0.27
    adona
    0.26
    FundMe
    0.24
     Obrador
    0.23
    ofus
    0.23
     Bourgoin
    0.23
    ็จ
    0.23
    บัติ
    0.23
     non
    0.22
    Activations Density 0.094%

    No Known Activations