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

    Neuronpedia

    Jacobian LensNEW
    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. 3-GEMMASCOPE-RES-16K
    11. 1369
    Prev
    Next
    INDEX
    Explanations

    references to New Zealand and related geopolitical or cultural terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.68
     smo
    -0.64
     оригіналу
    -0.64
    protoimpl
    -0.61
    rungsseite
    -0.61
    лъ
    -0.57
     FLO
    -0.57
    asen
    -0.57
    astéro
    -0.57
     ط
    -0.56
    POSITIVE LOGITS
     Zealand
    3.14
     ZEALAND
    2.36
     zealand
    1.98
     Zelanda
    1.95
     NZ
    1.87
    NZ
    1.87
    
    1.86
     Kiwi
    1.66
     Auckland
    1.51
    nz
    1.46
    Activations Density 0.079%

    No Known Activations