© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 803
    Prev
    Next
    INDEX
    Explanations

    expressions of hope and positive wishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leksikon
    -0.77
    dus
    -0.71
    richTextPanel
    -0.69
    Carthy
    -0.69
    --){
    -0.67
     Sac
    -0.67
    مج
    -0.65
    Rodriguez
    -0.64
     ویکی‌آمباردا
    -0.64
    quele
    -0.64
    POSITIVE LOGITS
     HOPE
    1.86
     hopes
    1.74
    HOPE
    1.72
     Hopes
    1.67
    hope
    1.66
     hope
    1.66
     Hope
    1.61
    Hope
    1.58
     hoped
    1.41
     hoping
    1.36
    Activations Density 0.040%

    No Known Activations