© 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. 8719
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of individuals and their roles or characteristics within a social or professional context

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

    Followed by "who" after a noun referring to a person

    np_acts-logits-general · gemini-2.0-flash

    someone who

    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
     nahilalakip
    -0.83
    writeFieldEnd
    -0.76
     CURIAM
    -0.69
    ArrowToggle
    -0.66
    цездатний
    -0.64
    IVEREF
    -0.64
     lenker
    -0.61
     utafiti
    -0.61
    ruptedException
    -0.59
    uron
    -0.57
    POSITIVE LOGITS
     who
    4.75
    who
    3.70
     whom
    3.13
    Who
    2.87
     quien
    2.81
     Who
    2.80
    whom
    2.63
     quienes
    2.35
     quién
    2.34
     którzy
    2.31
    Activations Density 1.352%

    No Known Activations