© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 886
    Prev
    Next
    INDEX
    Explanations

    references to elements such as nails in connection with studies on arsenic exposure and its effects on health

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

    fingernails, toenails, or nails

    np_acts-logits-general · gemini-2.0-flash

    fingernails and toenails

    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
    RenderAtEndOf
    -0.66
     Hershey
    -0.59
     testicular
    -0.58
     histamine
    -0.56
     brady
    -0.52
     Hugh
    -0.51
     resourceCulture
    -0.50
     hypothalamus
    -0.49
     Hampden
    -0.49
    timus
    -0.49
    POSITIVE LOGITS
     nail
    1.56
     nails
    1.52
     Nail
    1.42
    nails
    1.33
     Nails
    1.33
    nail
    1.30
     fingernails
    1.29
    Nail
    1.29
     manicure
    1.26
    Nails
    1.20
    Activations Density 0.128%

    No Known Activations