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. 405
    Prev
    Next
    INDEX
    Explanations

    attends to parenthetical or punctuation from the following token

    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
    0:0.07
    1:0.07
    2:0.05
    3:0.09
    4:0.19
    5:0.29
    6:0.12
    7:0.08
    Negative Logits
     itſelf
    -1.35
     myſelf
    -1.29
     Efq
    -1.22
     Monfieur
    -1.17
    AndEndTag
    -1.16
     ainfi
    -1.13
     ―――――
    -1.13
     doubtnut
    -1.10
     photolibrary
    -1.08
     Theſe
    -1.08
    POSITIVE LOGITS
     
    0.82
    <eos>
    0.77
     (
    0.75
    ↵
    0.69
     in
    0.67
     a
    0.64
    -
    0.61
     A
    0.60
     and
    0.59
     an
    0.59
    Activations Density 0.023%

    No Known Activations