© 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. 1576
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to transportation infrastructure and local government entities

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

    references to locations or geographic entities

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

    Ballymena and Northern Ireland

    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
    ScopeManager
    -0.74
     Gabon
    -0.61
     CPF
    -0.57
    MLLoader
    -0.57
    Personensuche
    -0.55
     Scud
    -0.55
    protoimpl
    -0.53
    hpur
    -0.53
     Salgado
    -0.52
     Gaut
    -0.51
    POSITIVE LOGITS
     Belfast
    1.13
    Belfast
    1.04
    derry
    0.84
     Ulster
    0.82
     Antrim
    0.81
    NI
    0.77
     belf
    0.75
     NI
    0.74
     DUP
    0.73
     Derry
    0.70
    Activations Density 0.105%

    No Known Activations