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. 2483
    Prev
    Next
    INDEX
    Explanations

    phrases indicating irritation or discomfort related to the skin or physical sensations

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

    Skin irritation, itchiness, and rashes

    np_acts-logits-general · gemini-2.0-flash

    skin irritation and itching

    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
    zygous
    -0.53
     gainera
    -0.52
    MemoryWarning
    -0.51
    TagMode
    -0.51
     vuotta
    -0.51
     تضيفلها
    -0.51
    KURZBESCHREIBUNG
    -0.50
    !("{
    -0.49
     ویکی‌پدیا
    -0.48
     ویکی‌پدیای
    -0.48
    POSITIVE LOGITS
     skin
    1.20
     Skin
    1.04
    Skin
    1.01
    skin
    0.97
     SKIN
    0.95
     itchy
    0.95
     irritation
    0.90
     skins
    0.90
     itching
    0.87
     itch
    0.84
    Activations Density 0.234%

    No Known Activations