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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15377
    Prev
    Next
    INDEX
    Explanations

    references to various roles and groups of people in professional and community contexts

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

    Occupations/roles followed by "who"

    np_acts-logits-general · gemini-2.0-flash

    relative pronouns after groups of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.83
    出版年
    -0.82
     مشين
    -0.71
    jetunion
    -0.69
     оригіналу
    -0.68
     kasarigan
    -0.68
     referenties
    -0.68
     ligiloj
    -0.67
    Viitteet
    -0.67
    itself
    -0.67
    POSITIVE LOGITS
     who
    1.69
     którzy
    1.24
     whom
    1.23
     kteří
    1.13
    who
    1.11
     ktorí
    0.99
     themselves
    0.96
     الذين
    0.92
     quienes
    0.90
    whom
    0.85
    Activations Density 0.877%

    No Known Activations