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. 8876
    Prev
    Next
    INDEX
    Explanations

    references to the day of the week, specifically Monday

    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
     Monday
    -1.55
    Monday
    -1.48
     Mondays
    -1.13
     monday
    -1.12
     MONDAY
    -1.02
    monday
    -1.00
     lunedì
    -0.98
     lundi
    -0.98
     lunes
    -0.94
    MONDAY
    -0.89
    POSITIVE LOGITS
     referenties
    0.57
     שוליים
    0.53
    initComponents
    0.52
    DispatchToProps
    0.50
    correctly
    0.46
    exitRule
    0.46
    ')):
    0.46
    :]:
    0.45
    kháu
    0.44
    èbres
    0.43
    Activations Density 0.124%

    No Known Activations