Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7705
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare, specifically focusing on employer-provided insurance and employee benefits

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

    Employee benefits and resources

    np_acts-logits-general · gemini-2.0-flash

    employee benefits and insurance

    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
    TagHelper
    -0.54
     étro
    -0.51
     Occupations
    -0.47
    LayoutStyle
    -0.47
    KommentareTeilen
    -0.46
    TextHelper
    -0.46
    pov
    -0.45
     Walkover
    -0.45
    Wyd
    -0.43
     Braut
    -0.43
    POSITIVE LOGITS
     benefits
    1.19
     perks
    1.04
     Benefits
    1.03
    benefits
    1.03
     benefit
    0.96
    Benefits
    0.95
     BENEFITS
    0.91
    BENEFITS
    0.89
    Benefit
    0.87
    benefit
    0.85
    Activations Density 0.167%

    No Known Activations