© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4353
    Prev
    Next
    INDEX
    Explanations

    terms related to compensation and payments within trust and property contexts

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

    Tokens related to payment or compensation

    np_acts-logits-general · gemini-2.0-flash

    paymentcompensationpayouts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kaufmann
    -0.32
     epidem
    -0.32
    Kauf
    -0.31
     hin
    -0.30
     Nieder
    -0.29
    まじ
    -0.29
    ανά
    -0.28
    Consumed
    -0.28
    Попис
    -0.28
    ukone
    -0.28
    POSITIVE LOGITS
     payouts
    1.23
     payout
    1.22
     cash
    1.16
     compensation
    1.06
     money
    1.04
    cash
    0.97
     payments
    0.96
    compensation
    0.95
     monetary
    0.94
     reward
    0.93
    Activations Density 0.433%

    No Known Activations