© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3617
    Prev
    Next
    INDEX
    Explanations

    terms associated with hospitals and medical facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Hospital" and related staff/resources

    np_acts-logits-general · gemini-2.0-flash

    hospital staff workers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     تضيفلها
    -0.90
     Chwiliwch
    -0.85
     createSlice
    -0.77
    adaptiveStyles
    -0.76
     propOrder
    -0.75
    WithMany
    -0.74
     مرئيه
    -0.74
     EconPapers
    -0.73
    autorest
    -0.72
    msgSender
    -0.71
    POSITIVE LOGITS
    ity
    0.69
    }*/
    0.55
    ない
    0.53
     dormitórios
    0.53
    \}=\
    0.52
    izations
    0.52
     estacionamento
    0.52
     wards
    0.51
    iers
    0.51
     Hil
    0.51
    Activations Density 0.137%

    No Known Activations