© 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. 1429
    Prev
    Next
    INDEX
    Explanations

    references to historical unions in Mexico

    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
    ніципалі
    -0.82
    EndGlobalSection
    -0.75
     pinulongan
    -0.75
    :✨
    -0.75
    PreferredItem
    -0.74
     disambiguazione
    -0.71
     seperate
    -0.70
     CreateTagHelper
    -0.70
     betweenstory
    -0.69
    henswürdigkeiten
    -0.69
    POSITIVE LOGITS
    ´
    0.60
     contemplates
    0.52
    Nowadays
    0.50
     viceversa
    0.47
     adecu
    0.46
     ideia
    0.46
     punctual
    0.46
    proy
    0.44
     frecu
    0.44
    estruct
    0.44
    Activations Density 1.950%

    No Known Activations