© 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 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. 67533
    Prev
    Next
    INDEX
    Explanations

    references to access tokens used for authentication

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

    access token, converting enzyme, plasminogen activator

    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
     Jank
    -0.55
    +#+#
    -0.51
     StatelessWidget
    -0.50
    complexContent
    -0.49
     Juan
    -0.47
    ViewFeatures
    -0.46
    drum
    -0.45
     Stony
    -0.44
     createState
    -0.44
     StatefulWidget
    -0.44
    POSITIVE LOGITS
     accessToken
    1.02
    accessToken
    0.88
    AccessToken
    0.75
     trône
    0.52
     AssemblyVersion
    0.49
     Wikipédia
    0.46
    parsedMessage
    0.46
     acompaña
    0.46
    acceso
    0.45
     gwiazd
    0.45
    Activations Density 0.001%

    No Known Activations