© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 92771
    Prev
    Next
    INDEX
    Explanations

    references to various roles or professions in research and healthcare contexts

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

    subjects of research or treatment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Gender and Occupation

    No Comments

    Negative Logits
    discovery
    -0.33
    Calculated
    -0.32
    Discovery
    -0.32
    achievement
    -0.32
    ძ
    -0.31
    müş
    -0.31
    recognition
    -0.31
     realization
    -0.31
     Diſ
    -0.31
     شع
    -0.31
    POSITIVE LOGITS
     participating
    1.17
     engaged
    0.98
     attending
    0.96
     visiting
    0.93
     undergoing
    0.92
     battling
    0.89
     who
    0.89
     entering
    0.88
     involved
    0.87
     pursuing
    0.87
    Activations Density 0.268%

    No Known Activations