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. 265
    Prev
    Next
    INDEX
    Explanations

    attends to mathematical notation and constants indicated by brackets in relation to the abstract structure or relationships within the same mathematical context

    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
    0:0.09
    1:0.03
    2:0.03
    3:0.04
    4:0.07
    5:0.04
    6:0.07
    7:0.59
    Negative Logits
     myſelf
    -1.59
     itſelf
    -1.55
     pleaſure
    -1.42
     Jefus
    -1.42
     ―――――
    -1.41
     themſelves
    -1.41
    ſelf
    -1.41
     Anſ
    -1.40
     Monfieur
    -1.39
    ſelves
    -1.38
    POSITIVE LOGITS
     
    0.84
    ↵↵
    0.77
     (
    0.75
     a
    0.73
     “
    0.70
     an
    0.69
     I
    0.68
     the
    0.68
    ,
    0.67
    <eos>
    0.66
    Activations Density 0.299%

    No Known Activations