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. 10-GEMMASCOPE-ATT-16K
    6. 6262
    Prev
    Next
    INDEX
    Explanations

    attends to roles related to teaching from operational elements related to performance

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.08
    2:0.08
    3:0.12
    4:0.10
    5:0.05
    6:0.26
    7:0.21
    Negative Logits
     autorytatywna
    -0.60
     doInBackground
    -0.57
    oredCriteria
    -0.53
     kasarigan
    -0.50
     AssemblyCulture
    -0.47
    aarrggbb
    -0.47
    IndentedString
    -0.47
    principalColumn
    -0.47
    RenderAtEndOf
    -0.47
    stateMutability
    -0.45
    POSITIVE LOGITS
    mäs
    0.26
     L
    0.23
    <eos>
    0.22
     $\
    0.21
     hin
    0.21
     E
    0.21
     diariamente
    0.21
      
    0.21
     Re
    0.21
     Service
    0.20
    Activations Density 0.136%

    No Known Activations