© 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. 14761
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals, particularly with the prefix "Mr." or variations of "Gr." and "Cr."

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

    starting with "Cr", "Gr", or "Kr"

    np_acts-logits-general · gemini-2.0-flash

    Cr, Gr, Kr prefixes

    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
    ex
    -0.76
     مرئيه
    -0.73
    اً
    -0.71
    ew
    -0.69
    ed
    -0.67
    eket
    -0.66
    ek
    -0.66
    ても
    -0.65
    ep
    -0.60
    ians
    -0.59
    POSITIVE LOGITS
    er
    0.61
    ang
    0.43
    n
    0.43
    ity
    0.43
    erii
    0.42
    ue
    0.41
    erar
    0.41
    angers
    0.40
     sortant
    0.39
    ondissement
    0.39
    Activations Density 0.243%

    No Known Activations