© 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. 40-GEMMASCOPE-RES-16K
    11. 902
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs, specifically those related to database interactions and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tasche
    -0.89
     occhiali
    -0.79
     prestazioni
    -0.76
     risorse
    -0.75
     secoli
    -0.71
     conseguenze
    -0.71
     operazioni
    -0.71
     vostri
    -0.69
     applicazioni
    -0.69
     cavalli
    -0.69
    POSITIVE LOGITS
     note
    0.49
     uz
    0.49
     pie
    0.49
     neat
    0.44
     vec
    0.43
     iz
    0.43
     pied
    0.42
     atti
    0.42
     aug
    0.40
     diem
    0.40
    Activations Density 0.151%

    No Known Activations