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. 396
    Prev
    Next
    INDEX
    Explanations

    attends to mathematical expressions or symbols from previously mentioned mathematical symbols or variables

    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
    1:0.18
    2:0.05
    3:0.03
    4:0.06
    5:0.30
    6:0.12
    7:0.18
    Negative Logits
    LookAnd
    -1.09
     autorytatywna
    -0.91
    rungsseite
    -0.90
     myſelf
    -0.89
     itſelf
    -0.88
     resourceCulture
    -0.87
     betweenstory
    -0.87
    bootstrapcdn
    -0.87
    ItemBackground
    -0.82
    StoryboardSegue
    -0.82
    POSITIVE LOGITS
    -
    0.64
    ,
    0.55
    '
    0.52
     
    0.50
    :
    0.49
    /
    0.45
     -
    0.44
    1
    0.43
    ↵↵
    0.43
    in
    0.41
    Activations Density 0.317%

    No Known Activations