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. 1635
    Prev
    Next
    INDEX
    Explanations

    medical conditions related to sleep apnea and its physiological impacts

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

    Throat, pharynx, and related anatomical terms

    np_acts-logits-general · gemini-2.0-flash

    throat, pharynx, larynx, salivary gland

    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
    RegressionTest
    -0.59
    writeFieldEnd
    -0.51
    poietic
    -0.50
     banho
    -0.50
     glú
    -0.50
    SequentialGroup
    -0.49
    tableFuture
    -0.47
    estacks
    -0.47
    TagMode
    -0.45
    iprot
    -0.45
    POSITIVE LOGITS
     throat
    1.20
     Throat
    1.13
     throats
    1.06
    throat
    1.06
     pharynx
    0.94
     saliva
    0.89
     Swallow
    0.85
     swallowing
    0.84
    arynx
    0.83
     larynx
    0.83
    Activations Density 0.633%

    No Known Activations