© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7832
    Prev
    Next
    INDEX
    Explanations

    references to "Northern" or related geographical 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
    clusal
    -0.71
     Penh
    -0.69
     Cun
    -0.69
     FCC
    -0.68
    AccessException
    -0.67
     Eilish
    -0.67
     AssemblyCulture
    -0.66
    cill
    -0.65
    httphttps
    -0.65
     Gabon
    -0.64
    POSITIVE LOGITS
     Northern
    2.79
    Northern
    2.67
     NORTHERN
    2.35
     northern
    2.25
    northern
    2.21
    北方
    1.15
     northerly
    1.11
    北部
    1.10
     northeastern
    1.04
     Northeastern
    0.94
    Activations Density 0.103%

    No Known Activations