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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73733
    Prev
    Next
    INDEX
    Explanations

    terms related to monads in programming or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gelände
    -0.55
    lewati
    -0.55
     getField
    -0.50
    detectChanges
    -0.50
     Turquía
    -0.49
    queryInterface
    -0.46
     béisbol
    -0.46
     soweit
    -0.46
    点此举报
    -0.46
     izquier
    -0.46
    POSITIVE LOGITS
     Mon
    0.95
     mon
    0.92
     MON
    0.87
    mon
    0.85
    Mon
    0.84
     Monday
    0.77
    monday
    0.74
    MON
    0.71
     monday
    0.71
    Monday
    0.69
    Activations Density 0.028%

    No Known Activations