© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7930
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically those related to "North" and its associated regions or countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Krakowie
    -0.95
    sstream
    -0.93
    %">
    -0.82
    Geplaatst
    -0.82
     Fij
    -0.81
     Lugano
    -0.80
    TestingModule
    -0.80
     Pacer
    -0.80
     Fiji
    -0.78
    ollectionView
    -0.78
    POSITIVE LOGITS
     North
    1.65
    north
    1.63
    North
    1.52
     north
    1.46
     NORTH
    1.43
    NORTH
    1.42
     Noth
    1.16
     Nort
    1.12
     Northern
    1.01
     norte
    0.97
    Activations Density 0.045%

    No Known Activations