© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 256
    Prev
    Next
    INDEX
    Explanations

    references to Minnesota locations and communities

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

    references to locations and educational institutions in Minnesota

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

    Minnesota and its cities

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     صوتيه
    -0.61
    DispatchToProps
    -0.56
     ZS
    -0.50
    interopRequire
    -0.50
     Eastwood
    -0.48
     Enzo
    -0.48
    গ্রহ
    -0.47
     Ons
    -0.47
    kier
    -0.47
    zysta
    -0.46
    POSITIVE LOGITS
     Minnesota
    1.51
    Minnesota
    1.38
     Minneapolis
    1.29
     MINNESOTA
    1.25
     MN
    1.22
     Minn
    1.16
    Minneapolis
    1.14
     Henne
    1.03
    MN
    1.00
    Minn
    1.00
    Activations Density 0.331%

    No Known Activations