Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 177
    Prev
    Next
    INDEX
    Explanations

    references to chronic pain and medical conditions

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

    doctors or medical procedures

    np_acts-logits-general · gemini-2.0-flash

    medical doctors

    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
    tagHelperRunner
    -0.83
    出版年
    -0.74
     disambiguazione
    -0.73
    iconque
    -0.69
    printLine
    -0.66
     ujednoznacz
    -0.65
    ⓘ
    -0.64
     Efq
    -0.62
    醐
    -0.61
     defaultstate
    -0.61
    POSITIVE LOGITS
     doctors
    1.15
    Doctors
    0.96
     Doctors
    0.89
    doctors
    0.82
     medically
    0.80
     doctor
    0.77
     dokter
    0.77
     physicians
    0.71
     médicos
    0.70
     Drs
    0.70
    Activations Density 0.479%

    No Known Activations