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 - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 61098
    Prev
    Next
    INDEX
    Explanations

    comparative phrases, particularly the word "versus"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    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

    Negative Logits
     versus
    -1.29
    ."),
    -1.15
    %");
    -1.13
    )"),
    -1.12
    "},
    
    -1.12
    '},
    
    -1.10
    ."));
    -1.09
    )");
    
    -1.06
    ()");
    -1.05
    .");
    
    -1.05
    POSITIVE LOGITS
     mẽ
    0.82
    oceros
    0.79
    roleum
    0.75
     elever
    0.73
    UserScript
    0.73
     épu
    0.72
     mondial
    0.69
     XCTest
    0.68
     hés
    0.68
    numberOfLines
    0.68
    Activations Density 0.013%

    No Known Activations