© 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. 37-GEMMASCOPE-RES-16K
    11. 1148
    Prev
    Next
    INDEX
    Explanations

    references to new experiences or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.44
     للاسماء
    -0.41
     intptr
    -0.41
     contextLoads
    -0.40
    AddTagHelper
    -0.39
    RegistryLite
    -0.38
    istoitu
    -0.38
     Allociné
    -0.36
    hiel
    -0.36
     autorytatywna
    -0.35
    POSITIVE LOGITS
     new
    3.77
    new
    3.00
     nieuwe
    2.97
     nuevos
    2.86
     nuevas
    2.80
     nuovi
    2.80
     nueva
    2.78
     neuen
    2.77
    新的
    2.77
     nuove
    2.75
    Activations Density 3.491%

    No Known Activations