© 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. 10078
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations and their interactions or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     băr
    -0.47
     dezelve
    -0.47
     zoude
    -0.41
     zelve
    -0.41
    awaiter
    -0.40
     niega
    -0.40
     eenen
    -0.40
     cherchés
    -0.39
    springer
    -0.39
     voorbij
    -0.39
    POSITIVE LOGITS
    principalTable
    0.60
    ViewImports
    0.52
     bernama
    0.51
    CloseOperation
    0.50
     called
    0.50
     lenker
    0.49
     named
    0.49
     namely
    0.48
    名叫
    0.46
     Namely
    0.45
    Activations Density 0.615%

    No Known Activations