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. 6055
    Prev
    Next
    INDEX
    Explanations

    attends to token colors from royal or noble heritage 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
    2:0.10
    3:0.12
    4:0.13
    5:0.06
    6:0.21
    7:0.16
    Negative Logits
     loob
    -0.23
    ieteur
    -0.23
    Tikang
    -0.21
    kasten
    -0.21
    forKey
    -0.20
    NameInMap
    -0.20
    Xk
    -0.20
    Autoritní
    -0.19
    onee
    -0.19
     Mün
    -0.18
    POSITIVE LOGITS
    GOTREF
    0.49
    migrationBuilder
    0.46
    Sklici
    0.39
    pnea
    0.37
    Przypisy
    0.37
     numberWith
    0.36
    SourceChecksum
    0.35
    modelBuilder
    0.35
     financières
    0.34
     âgées
    0.34
    Activations Density 0.023%

    No Known Activations