© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28955
    Prev
    Next
    INDEX
    Explanations

    terms related to social roles and professions

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

    people who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.72
    Personendaten
    -0.71
    migrationBuilder
    -0.71
     Taktlose
    -0.69
     GenerationType
    -0.68
     &___
    -0.66
    ########.
    -0.64
     Roskov
    -0.63
    addGap
    -0.63
    tschaft
    -0.63
    POSITIVE LOGITS
     who
    1.32
    who
    0.98
     whom
    0.95
     którzy
    0.85
     ktorí
    0.80
     kteří
    0.80
     quienes
    0.77
     whoſe
    0.71
    whom
    0.71
    Who
    0.70
    Activations Density 0.396%

    No Known Activations