© 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. 410
    Prev
    Next
    INDEX
    Explanations

    phrases urging readers to seek medical guidance or assistance

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

    doctors or physicians

    np_acts-logits-general · gemini-2.0-flash

    your doctor

    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
    DockStyle
    -0.90
     ujednoznacz
    -0.82
    RegressionTest
    -0.80
    ագրություններ
    -0.73
    存于互联网档案馆
    -0.71
     ExecuteAsync
    -0.66
    STAFF
    -0.65
    tagext
    -0.65
     Apprentices
    -0.63
     orphans
    -0.62
    POSITIVE LOGITS
     doctor
    1.27
     physician
    1.03
     doctors
    0.97
    doctor
    0.94
     Doctor
    0.94
     médecin
    0.93
     local
    0.88
     dokter
    0.88
     médico
    0.83
    医生
    0.82
    Activations Density 0.275%

    No Known Activations