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. 450
    Prev
    Next
    INDEX
    Explanations

    attends to terminal punctuation or string delimiters from preceding code or configuration elements

    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
    1:0.07
    2:0.10
    3:0.18
    4:0.08
    5:0.05
    6:0.36
    7:0.10
    Negative Logits
     itſelf
    -0.93
    ^(@)
    -0.91
     myſelf
    -0.90
     $_"
    -0.88
    >\<^
    -0.82
    ."</
    -0.81
     themſelves
    -0.80
    $.
    
    -0.79
    PreferredItem
    -0.79
    .}~\
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.65
    .
    0.63
    ,
    0.61
    <eos>
    0.56
    (
    0.54
     (
    0.54
     “
    0.53
     or
    0.52
     "
    0.51
     and
    0.48
    Activations Density 0.267%

    No Known Activations