© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9242
    Prev
    Next
    INDEX
    Explanations

    different sections or segments in a structured text or data format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.69
    RegressionTest
    -0.67
    Географиясе
    -0.64
    adaptiveStyles
    -0.61
    IndentedString
    -0.58
    contentLoaded
    -0.57
    PreferredItem
    -0.56
    RotationOrder
    -0.56
     CreateTagHelper
    -0.56
     createSprite
    -0.55
    POSITIVE LOGITS
     Gegenteil
    0.44
     comunión
    0.42
    Atentamente
    0.42
     Sortiment
    0.42
     Voraus
    0.40
     Lingkungan
    0.40
    AMIENTO
    0.40
     Utama
    0.39
     Anbau
    0.39
     Privacidad
    0.39
    Activations Density 0.481%

    No Known Activations