© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15794
    Prev
    Next
    INDEX
    Explanations

    numerical data and financial information

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

    references to Canada and Canadian institutions or geographic locations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utilised
    -0.67
    Organis
    -0.66
     minimise
    -0.66
     organising
    -0.65
     organised
    -0.63
     recognises
    -0.63
     utilising
    -0.62
    organised
    -0.62
     Organis
    -0.62
     optimised
    -0.62
    POSITIVE LOGITS
     Canada
    1.59
     Canadian
    1.55
     Canadians
    1.50
    Canada
    1.46
    Canadian
    1.41
     Canadá
    1.30
    カナダ
    1.27
     canadian
    1.25
     CANADA
    1.25
    加拿大
    1.24
    Activations Density 0.181%

    No Known Activations