Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16107
    Prev
    Next
    INDEX
    Explanations

    references to toilet training or bathroom-related activities and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    shadowOpacity
    -0.54
    RRect
    -0.53
    Xna
    -0.52
     الحره
    -0.49
     vectorielles
    -0.48
     CreateTagHelper
    -0.47
     disambiguazione
    -0.45
    Chham
    -0.44
    PositiveButton
    -0.44
    baran
    -0.43
    POSITIVE LOGITS
     toilet
    0.96
     Toilet
    0.88
     toilets
    0.87
    toilet
    0.79
    Toilet
    0.78
     urinary
    0.68
     restroom
    0.67
     potty
    0.66
     bathroom
    0.66
     toilettes
    0.65
    Activations Density 0.213%

    No Known Activations