© 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. 101727
    Prev
    Next
    INDEX
    Explanations

    programming functions and their control structures

    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
     informée
    -0.44
     alimentaire
    -0.43
    sapat
    -0.42
     européens
    -0.42
     transferencia
    -0.41
     personnalisée
    -0.41
     déta
    -0.41
     continuare
    -0.41
     puesta
    -0.40
     förslag
    -0.40
    POSITIVE LOGITS
    sizeCache
    0.54
    TagMode
    0.49
    :✨
    0.47
    bootstrapcdn
    0.43
    istoitu
    0.42
    XmlAccessType
    0.42
    nloa
    0.41
     ModelExpression
    0.40
    HIL
    0.39
    TestingModule
    0.38
    Activations Density 0.054%

    No Known Activations