© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 56877
    Prev
    Next
    INDEX
    Explanations

    verbs related to changing states or conditions, particularly involving returning to a previous state

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

    resort or revert to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     itſelf
    -0.75
     ſon
    -0.75
     Inſ
    -0.73
    ImageContext
    -0.72
     JAXB
    -0.72
     onData
    -0.71
     faſt
    -0.71
     ſch
    -0.71
     blumen
    -0.70
     ſy
    -0.70
    POSITIVE LOGITS
    revert
    0.64
     revert
    0.63
     recurrir
    0.60
     resorted
    0.59
     reverted
    0.58
     reverting
    0.54
     resorting
    0.54
    fallback
    0.50
     fallback
    0.46
     reversion
    0.44
    Activations Density 0.019%

    No Known Activations