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. 113
    Prev
    Next
    INDEX
    Explanations

    attends to programming-related tokens from specific data type tokens

    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
    1:0.02
    2:0.09
    3:0.26
    4:0.11
    5:0.15
    6:0.13
    7:0.15
    Negative Logits
    ,
    -0.36
     be
    -0.32
     he
    -0.32
     this
    -0.30
     i
    -0.29
     co
    -0.29
     to
    -0.29
     (
    -0.28
     F
    -0.28
     im
    -0.28
    POSITIVE LOGITS
     Efq
    0.56
     houſe
    0.56
     Shaksp
    0.56
     myſelf
    0.56
     zirc
    0.55
     Monfieur
    0.54
     Shakspeare
    0.53
     becauſe
    0.52
     ſind
    0.52
    }{*}{
    0.52
    Activations Density 0.036%

    No Known Activations