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. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8882
    Prev
    Next
    INDEX
    Explanations

    references to airports and airlines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     airport
    -1.89
     Airport
    -1.72
    airport
    -1.51
    Airport
    -1.48
     airports
    -1.27
     aeropuerto
    -1.21
     aeroporto
    -1.11
     Airports
    -1.09
     Flughafen
    -1.09
    机场
    -1.02
    POSITIVE LOGITS
    ukone
    0.60
    kloped
    0.53
     ویکی‌پدیای
    0.50
    adə
    0.50
    "){
    
    0.49
    '>{
    0.49
    tablename
    0.49
    kkue
    0.49
    `;
    
    0.49
     postIndex
    0.48
    Activations Density 0.125%

    No Known Activations