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. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10460
    Prev
    Next
    INDEX
    Explanations

    terms related to disinfectants and their efficacy in clinical settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vinci
    -0.57
    tvguidetime
    -0.50
     iNdEx
    -0.49
    olstadt
    -0.49
    ngrx
    -0.48
    piac
    -0.48
     Velvet
    -0.48
     polenta
    -0.48
    colgroup
    -0.48
    matite
    -0.48
    POSITIVE LOGITS
     disinfection
    1.07
     disinfect
    1.04
     sterilization
    0.99
     kill
    0.99
     saniti
    0.99
     sterili
    0.97
     kills
    0.96
     disinfectant
    0.95
     killing
    0.94
     sanitizer
    0.92
    Activations Density 0.463%

    No Known Activations