© 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. 33-GEMMASCOPE-RES-16K
    11. 254
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terms associated with music categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Umum
    -0.81
     Bidang
    -0.80
     Lingkungan
    -0.79
     Komunikasi
    -0.77
     Masyarakat
    -0.77
     hendes
    -0.76
     kvinder
    -0.76
     Hidup
    -0.74
     Keuangan
    -0.73
     spørs
    -0.73
    POSITIVE LOGITS
     geograf
    0.59
     med
    0.57
     prak
    0.54
     tacto
    0.54
     hybride
    0.52
     kaos
    0.52
     moti
    0.51
     organiser
    0.51
     terapi
    0.50
     slags
    0.50
    Activations Density 0.043%

    No Known Activations