© 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. 34-GEMMASCOPE-RES-16K
    11. 11439
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and queries involving calculations, especially related to multiplication and division

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     übrigens
    -0.56
     ainfi
    -0.53
     libremente
    -0.51
     étoit
    -0.51
     ligeramente
    -0.50
     nejen
    -0.50
     suficientemente
    -0.50
     Flucht
    -0.49
     desmotivaciones
    -0.48
     aparentemente
    -0.48
    POSITIVE LOGITS
     OFDb
    0.55
     vPvB
    0.52
    antd
    0.52
    jspb
    0.51
     pareil
    0.50
     cherchés
    0.49
     mien
    0.48
    瞧
    0.48
     famí
    0.48
    ppuden
    0.48
    Activations Density 1.091%

    No Known Activations