© 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. 10625
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical expressions or operations indicating definitions or conclusions

    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
    SequentialGroup
    -0.83
     EconPapers
    -0.75
    évaluateur
    -0.75
     kasarigan
    -0.73
    Бахар
    -0.72
     kaarangay
    -0.71
     دیکھیے
    -0.71
    fjspx
    -0.70
    awtextra
    -0.69
     ligiloj
    -0.69
    POSITIVE LOGITS
    {
    0.43
    ítě
    0.28
    end
    0.26
     adopción
    0.24
     komunitas
    0.24
     turísticos
    0.23
     parfaite
    0.23
    item
    0.23
     présidenti
    0.22
     käyt
    0.22
    Activations Density 0.011%

    No Known Activations