© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102341
    Prev
    Next
    INDEX
    Explanations

    financial or monetary terms and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     esternos
    -0.82
    rungsseite
    -0.75
     kasarigan
    -0.73
     للمعارف
    -0.73
     wikipagina
    -0.71
    MigrationBuilder
    -0.71
     EconPapers
    -0.71
     informée
    -0.69
    IsContent
    -0.68
     تضيفلها
    -0.68
    POSITIVE LOGITS
    7
    0.83
     seven
    0.67
     Seven
    0.66
    七
    0.58
    Seven
    0.56
     SEVEN
    0.52
    6
    0.52
     siete
    0.51
     sieben
    0.50
     Six
    0.49
    Activations Density 0.085%

    No Known Activations