© 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. 20-GEMMASCOPE-RES-16K
    11. 7189
    Prev
    Next
    INDEX
    Explanations

    phrases associated with parameters and results in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    commas, especially in citations, legal references, and document formatting.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.47
     OFDb
    -0.39
     desertcart
    -0.39
     either
    -0.37
    principalTable
    -0.37
    Rohy
    -0.35
     Monfieur
    -0.35
     Și
    -0.34
     whichever
    -0.34
     funcionales
    -0.34
    POSITIVE LOGITS
    rungsseite
    0.70
     kaarangay
    0.63
     lenker
    0.58
    SharedDtor
    0.56
    RuleContext
    0.52
     disambiguazione
    0.51
    ventes
    0.50
     ujednoznacz
    0.50
     kasarigan
    0.48
     migli
    0.48
    Activations Density 0.092%

    No Known Activations