© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 3301
    Prev
    Next
    INDEX
    Explanations

    references to bathroom-related features and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    談社
    -0.81
    loem
    -0.64
    phazard
    -0.63
     scaff
    -0.63
    orsese
    -0.62
    endell
    -0.62
    orestation
    -0.62
    alsch
    -0.61
     Parkinson
    -0.61
     RouterModule
    -0.59
    POSITIVE LOGITS
     bath
    1.09
     baths
    1.02
     bathing
    1.01
     bathe
    0.98
     swimmers
    0.97
     Swim
    0.92
    浴
    0.90
     Baths
    0.90
     swim
    0.89
    Swim
    0.88
    Activations Density 0.128%

    No Known Activations