© 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. 39-GEMMASCOPE-RES-16K
    11. 4429
    Prev
    Next
    INDEX
    Explanations

    references to dining experiences and food choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.61
    WriteTagHelper
    -0.58
    ----</
    -0.56
    лтемелер
    -0.56
    Notae
    -0.54
    vocable
    -0.52
     Wikimedijinoj
    -0.50
     незавершена
    -0.48
     &___
    -0.48
    CodeAttribute
    -0.46
    POSITIVE LOGITS
     promo
    0.49
     promotion
    0.48
     promotions
    0.44
     Etude
    0.43
    athione
    0.43
     branch
    0.43
     nett
    0.42
     promos
    0.41
     Promotion
    0.41
     menta
    0.40
    Activations Density 0.343%

    No Known Activations