© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7849
    Prev
    Next
    INDEX
    Explanations

    elements related to employment status and job positions

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

    Employment types (permanent, contractors, employees)

    np_acts-logits-general · gemini-2.0-flash

    permanent employment status

    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
     harten
    -0.48
    arget
    -0.48
    ScopeManager
    -0.46
    enetrable
    -0.46
    UpInside
    -0.46
     desar
    -0.46
     lourdes
    -0.46
     Markup
    -0.45
    Commander
    -0.45
    rima
    -0.45
    POSITIVE LOGITS
     hired
    1.27
     employed
    1.20
     contract
    1.13
     permanent
    1.13
     hire
    1.13
     contracted
    1.11
     salaried
    1.09
    employed
    1.05
     hires
    1.04
    permanent
    1.03
    Activations Density 0.280%

    No Known Activations