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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6635
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to bathrooms, toilet usage, and urinary functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.53
    urtstag
    -0.53
    addComponent
    -0.52
     Roskov
    -0.52
     صوتيه
    -0.51
     herald
    -0.50
     silks
    -0.50
    kaper
    -0.50
    fras
    -0.49
    lexia
    -0.49
    POSITIVE LOGITS
     toilet
    1.35
     toilets
    1.26
     Toilet
    1.23
    Toilet
    1.23
    toilet
    1.22
     restroom
    1.08
     bathroom
    1.06
    🚽
    1.03
     bathrooms
    0.98
     excretion
    0.97
    Activations Density 0.182%

    No Known Activations