© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12282
    Prev
    Next
    INDEX
    Explanations

    financial terms related to capital expenditures and obligations

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

    Capital assets and expenditures

    np_acts-logits-general · gemini-2.0-flash

    capital expenditures and assets

    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
    bootstrapcdn
    -0.77
    WithFormat
    -0.59
    HandlerContext
    -0.51
    Personendaten
    -0.50
     ciudadana
    -0.49
    RTHOOK
    -0.46
    CloseOperation
    -0.45
     réfugi
    -0.43
    RenderAtEndOf
    -0.43
     mergeFrom
    -0.42
    POSITIVE LOGITS
     depre
    1.26
     depreciation
    1.17
     asset
    1.02
     Depreciation
    0.96
    depre
    0.94
     equipment
    0.92
     Equipment
    0.87
     Asset
    0.87
     capital
    0.87
     fleet
    0.87
    Activations Density 0.175%

    No Known Activations