© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12131
    Prev
    Next
    INDEX
    Explanations

    topics related to work and employment impacts

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

    Terms related to labor and employment

    np_acts-logits-general · gemini-2.0-flash

    work, employment, and workplaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    BeginInit
    -0.44
     romántico
    -0.40
     popularidad
    -0.36
    rboles
    -0.35
    Hozzáférés
    -0.35
     Agung
    -0.33
    ientôt
    -0.33
    곡
    -0.32
    rvore
    -0.32
     sélectionner
    -0.32
    POSITIVE LOGITS
     employers
    0.83
     workplace
    0.82
     workplaces
    0.78
     employe
    0.77
    Workplace
    0.73
     employes
    0.71
     Workplace
    0.71
     employer
    0.71
    職場
    0.69
    employment
    0.69
    Activations Density 0.362%

    No Known Activations