© 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. 41-GEMMASCOPE-RES-16K
    11. 7989
    Prev
    Next
    INDEX
    Explanations

    coding problems related to variables and functions in programming discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.58
     рекоменду
    -0.44
     heeft
    -0.43
     själva
    -0.43
    UrlResolution
    -0.43
    новниш
    -0.42
     चाहते
    -0.41
     themselves
    -0.40
     pihaknya
    -0.40
    [:,:,
    -0.39
    POSITIVE LOGITS
     myself
    1.22
     saya
    0.83
    myself
    0.80
     tôi
    0.78
     tengo
    0.77
     אני
    0.75
     mám
    0.74
    私は
    0.73
     vagyok
    0.71
     jsem
    0.69
    Activations Density 0.091%

    No Known Activations