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. 6127
    Prev
    Next
    INDEX
    Explanations

    attends to the token "Sprite" from related tokens that represent sprite functions

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.54
    4:0.10
    5:0.05
    6:0.08
    7:0.07
    Negative Logits
     itſelf
    -0.96
     myſelf
    -0.94
     Monfieur
    -0.87
    ſelf
    -0.85
    ſelves
    -0.83
     Jefus
    -0.82
     Efq
    -0.82
     Theſe
    -0.81
     Anſ
    -0.79
     leaſt
    -0.79
    POSITIVE LOGITS
     
    0.48
     (
    0.47
    ;
    0.44
     I
    0.42
     '
    0.41
     T
    0.41
     -
    0.41
      
    0.41
    ,
    0.40
    …
    0.40
    Activations Density 0.058%

    No Known Activations