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. 8760
    Prev
    Next
    INDEX
    Explanations

    references to family relationships, particularly involving the term 'mom'

    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
    了
    -1.80
     了
    -1.32
    mybatisplus
    -0.85
     الحره
    -0.83
    了她
    -0.80
    了的
    -0.77
    了我
    -0.77
     للاسماء
    -0.77
     AssemblyProduct
    -0.72
    了你
    -0.71
    POSITIVE LOGITS
     poils
    0.56
     conduire
    0.55
    ']))
    
    0.54
     vœux
    0.54
     Wikiseite
    0.52
     laikā
    0.52
    '])){
    
    0.50
     Vikipedi
    0.48
     until
    0.47
    tiden
    0.47
    Activations Density 0.102%

    No Known Activations