© 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. 3958
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and graduation-related activities

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

    Oklahoma and cities within it

    np_acts-logits-general · gemini-2.0-flash

    Oklahoma cities and places

    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
     Nantucket
    -0.65
    Brunswick
    -0.59
     Weymouth
    -0.58
     sánh
    -0.54
    Fanny
    -0.53
    })$}
    -0.52
     VDC
    -0.52
     cantons
    -0.51
     cranberry
    -0.51
     Dijon
    -0.51
    POSITIVE LOGITS
     Oklahoma
    1.47
    Oklahoma
    1.33
     Okla
    1.15
     OK
    1.07
     Tulsa
    1.03
     Edmond
    1.00
     Ok
    0.98
    lahoma
    0.98
    LAHOMA
    0.97
    Tul
    0.86
    Activations Density 0.150%

    No Known Activations