© 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. 14-GEMMASCOPE-RES-16K
    11. 3650
    Prev
    Next
    INDEX
    Explanations

    terms related to financial capital and expenditures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.82
     Flücht
    -0.80
    noaa
    -0.78
     Toussaint
    -0.76
    Vidite
    -0.71
    jería
    -0.69
     Feynman
    -0.68
     Nose
    -0.68
     Jennings
    -0.67
     Aç
    -0.67
    POSITIVE LOGITS
    CAPITAL
    1.23
     capital
    1.22
     CAPITAL
    1.21
     Capital
    1.16
    capital
    1.15
    Capital
    1.11
     kapital
    1.06
     capitales
    1.02
    kapital
    1.00
     capitals
    0.99
    Activations Density 0.057%

    No Known Activations