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. 20-GEMMASCOPE-RES-16K
    6. 4651
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and treatments

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

    Transplants and related immunological responses

    np_acts-logits-general · gemini-2.0-flash

    organ transplant and incompatibility

    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
     AssemblyCulture
    -0.73
     nahilalakip
    -0.67
     fleas
    -0.67
     InputDecoration
    -0.65
     '\\;'
    -0.64
    phonie
    -0.63
    meanor
    -0.58
     SEDS
    -0.58
    DoubleQuotes
    -0.57
     handcuffs
    -0.57
    POSITIVE LOGITS
     donor
    1.52
     Donor
    1.38
     transplant
    1.35
     organ
    1.29
     Transplant
    1.29
    donor
    1.29
    Donor
    1.28
     donors
    1.28
     transplantation
    1.19
     Transplantation
    1.19
    Activations Density 0.563%

    No Known Activations