© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6907
    Prev
    Next
    INDEX
    Explanations

    phrases related to employee health and workplace conditions

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

    preceding "work" or "workplace"

    np_acts-logits-general · gemini-2.0-flash

    work and workplace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.66
    \{\\
    -0.62
    zzlies
    -0.60
    曖昧さ回避
    -0.59
     >=",
    -0.58
     GenerationType
    -0.56
     LoggerFactory
    -0.56
    ])));
    -0.55
    rungsseite
    -0.54
    NewUrlParser
    -0.54
    POSITIVE LOGITS
     workplace
    1.72
     work
    1.57
     workplaces
    1.49
     Workplace
    1.41
    work
    1.35
    Work
    1.31
     Work
    1.30
     WORK
    1.30
     kerja
    1.22
    工作
    1.22
    Activations Density 0.303%

    No Known Activations