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. 0-GEMMASCOPE-ATT-16K
    6. 6129
    Prev
    Next
    INDEX
    Explanations

    attends to the digit "9" from subsequent tokens represented by digits "5" or "6"

    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
    0:0.02
    1:0.04
    2:0.02
    3:0.02
    4:0.02
    5:0.02
    6:0.01
    7:0.81
    Negative Logits
     purpoſe
    -1.50
     itſelf
    -1.47
     Efq
    -1.46
     Monfieur
    -1.46
     myſelf
    -1.46
     ſeveral
    -1.45
     raiſ
    -1.44
     themſelves
    -1.41
     ſtate
    -1.41
     Shakspeare
    -1.39
    POSITIVE LOGITS
     [
    0.76
     (
    0.73
    ,
    0.71
     in
    0.68
     van
    0.67
     I
    0.67
     R
    0.66
     r
    0.66
     -
    0.65
     la
    0.65
    Activations Density 0.433%

    No Known Activations