© 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. 10424
    Prev
    Next
    INDEX
    Explanations

    an emphasis on historical and organizational details

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

    relating to local places or communities

    np_acts-logits-general · gemini-2.0-flash

    local places and entities

    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
     Maori
    -0.61
     Etrus
    -0.58
     Inca
    -0.58
     Lordships
    -0.57
     Confucius
    -0.57
     Confucian
    -0.57
     Mayan
    -0.55
     Rohing
    -0.53
     Jedi
    -0.53
    ędzynarod
    -0.52
    POSITIVE LOGITS
     downtown
    1.02
     local
    1.01
     town
    0.95
    เมือง
    0.86
     city
    0.85
     hometown
    0.83
     locals
    0.83
    locally
    0.82
     शहर
    0.82
     towns
    0.80
    Activations Density 1.102%

    No Known Activations