© 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. 5869
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating significance or importance in the context being described

    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
    Hentet
    -0.62
     linkovi
    -0.55
     مرئيه
    -0.51
     resourceCulture
    -0.49
    raire
    -0.47
    OGND
    -0.44
    adaptiveStyles
    -0.43
    씩
    -0.43
    Cyfeiriadau
    -0.41
    ClientSize
    -0.40
    POSITIVE LOGITS
     main
    2.25
     principale
    2.14
     principal
    2.08
     principaux
    2.03
     principales
    2.00
     głów
    1.98
     principais
    1.98
     principali
    1.95
     utama
    1.95
     chief
    1.86
    Activations Density 1.100%

    No Known Activations