© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58500
    Prev
    Next
    INDEX
    Explanations

    references to bonuses and incentive structures in a work context

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

    extra payments or penalties

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    cle
    -0.43
     Bör
    -0.42
     Bill
    -0.41
    Bill
    -0.40
     Dore
    -0.40
    Cle
    -0.40
     AppCompatTheme
    -0.40
     hell
    -0.39
    contentLoaded
    -0.39
     Ph
    -0.37
    POSITIVE LOGITS
     zusätzlichen
    0.61
     bonuses
    0.57
     overtime
    0.55
     EXTRA
    0.54
     tambahan
    0.53
    TargetException
    0.52
    extra
    0.52
     bonus
    0.51
     zusätzliche
    0.50
     surcharge
    0.50
    Activations Density 0.024%

    No Known Activations