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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27321
    Prev
    Next
    INDEX
    Explanations

    references to job statistics and employment trends

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

    jobs and unemployment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ссора
    -0.41
     tasteful
    -0.40
     aesthetic
    -0.38
     spese
    -0.37
    impl
    -0.37
    團隊
    -0.36
     billing
    -0.36
    None
    -0.36
     bels
    -0.36
     tasteless
    -0.36
    POSITIVE LOGITS
     unemployment
    1.30
     Unemployment
    1.17
     employment
    1.14
     Employment
    1.13
    Unemployment
    1.11
     employers
    1.10
     jobs
    1.08
     job
    1.06
     unemployed
    1.04
     jobless
    1.03
    Activations Density 0.088%

    No Known Activations