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. 149
    Prev
    Next
    INDEX
    Explanations

    attends to locations marked by the tokens "Kansas" from specific tokens indicating larger cities

    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
    0:0.03
    1:0.02
    2:0.04
    3:0.03
    4:0.15
    5:0.63
    6:0.03
    7:0.03
    Negative Logits
    GEBURTSDATUM
    -0.76
     themſelves
    -0.71
     Anſ
    -0.71
     Forumite
    -0.71
     ―――――
    -0.70
     itſelf
    -0.69
     Efq
    -0.69
    SharedDtor
    -0.68
    ſelves
    -0.68
    ſelf
    -0.68
    POSITIVE LOGITS
    ↵
    0.42
     of
    0.37
    .
    0.37
    -
    0.36
    /
    0.36
     in
    0.33
     the
    0.33
     =
    0.31
     or
    0.28
    ,
    0.28
    Activations Density 2.787%

    No Known Activations