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. 3077
    Prev
    Next
    INDEX
    Explanations

    medical terms and references related to thyroid conditions and diagnostics

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

    the thyroid and iodine

    np_acts-logits-general · gemini-2.0-flash

    thyroid gland conditions and iodine

    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
    Gambas
    -0.78
     pinulongan
    -0.63
     Acosta
    -0.56
    tagHelperRunner
    -0.53
     DBNull
    -0.52
     Limburg
    -0.52
     يتيمه
    -0.51
     Angola
    -0.51
    
    -0.51
    eroon
    -0.50
    POSITIVE LOGITS
     thyroid
    1.04
     Thyroid
    0.95
     thy
    0.87
    thyroid
    0.87
    Thy
    0.80
     TSH
    0.80
     iodine
    0.79
     THY
    0.77
     Hashimoto
    0.77
    thyroidism
    0.75
    Activations Density 0.323%

    No Known Activations