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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10184
    Prev
    Next
    INDEX
    Explanations

    negative traits or behaviors in social interactions, particularly in the workplace

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

    sexual harassment and workplace problems

    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
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.68
    HtmlAttribute
    -0.48
     nahilalakip
    -0.43
    CrossRef
    -0.42
     autorytatywna
    -0.42
     jeugd
    -0.40
     prijzen
    -0.38
     výstav
    -0.38
    addCriterion
    -0.37
     appelez
    -0.37
    POSITIVE LOGITS
     workplace
    1.95
     employee
    1.73
    Workplace
    1.71
     Workplace
    1.70
     Employee
    1.63
     employees
    1.61
    Employee
    1.56
     coworker
    1.51
    Employees
    1.51
     Employees
    1.51
    Activations Density 0.729%

    No Known Activations