© 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. 31-GEMMASCOPE-RES-16K
    11. 10550
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to environmental and sustainability issues

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

    quoted phrases or terms that are conceptually significant or labeled with quotation marks.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pří
    -0.32
    området
    -0.31
     Höchst
    -0.30
     zugelassen
    -0.29
     personlig
    -0.28
     avanzada
    -0.28
    Paged
    -0.27
     colectiva
    -0.27
     independiente
    -0.27
     suminist
    -0.27
    POSITIVE LOGITS
    +#+#
    0.78
     sogenannten
    0.76
     tzw
    0.76
     infamous
    0.75
     sogenannte
    0.75
    contentLoaded
    0.73
    bootstrapcdn
    0.72
     @"/
    0.72
    $_['
    0.71
     Italijanski
    0.71
    Activations Density 0.865%

    No Known Activations