© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 101781
    Prev
    Next
    INDEX
    Explanations

    references to income and financial concepts

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

    income tax returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    épa
    -0.38
     PROPER
    -0.38
    épaisseur
    -0.37
     thoroughly
    -0.37
     Valentín
    -0.36
    sigue
    -0.36
    sailor
    -0.36
    zcze
    -0.35
     DATES
    -0.35
     constru
    -0.34
    POSITIVE LOGITS
     income
    1.22
     Income
    1.16
    Income
    1.09
    income
    1.03
     INCOME
    1.02
     revenus
    0.99
     revenue
    0.97
     incomes
    0.95
     revenu
    0.93
     Revenue
    0.90
    Activations Density 0.025%

    No Known Activations