© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14849
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly of people and places

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

    Feminine names

    np_acts-logits-general · gemini-2.0-flash

    female given names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.71
     AssemblyCulture
    -0.68
    AndEndTag
    -0.57
    ‍♂️
    -0.56
     Walkover
    -0.52
    WireFormatLite
    -0.51
    antMatchers
    -0.51
     opérateur
    -0.50
     disponibilités
    -0.50
     Mr
    -0.50
    POSITIVE LOGITS
    abelle
    0.66
    alee
    0.65
    ilyn
    0.65
    chelle
    0.64
    leen
    0.63
    lyn
    0.62
    lynn
    0.61
    elyn
    0.61
    iann
    0.61
    ielle
    0.60
    Activations Density 0.134%

    No Known Activations