© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 110266
    Prev
    Next
    INDEX
    Explanations

    references to prominent individuals, particularly Bill Gates and his philanthropic efforts

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

    bill gates' statements and actions

    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
     surla
    -0.76
    RegressionTest
    -0.52
    LookAnd
    -0.52
    oa̍t
    -0.50
    Diweddarwch
    -0.49
    rrggbb
    -0.47
     ***!
    -0.47
    ContentAsync
    -0.45
     siquiera
    -0.44
    SourceChecksum
    -0.44
    POSITIVE LOGITS
     Gates
    0.62
    Gates
    0.60
     Microsoft
    0.56
     Melinda
    0.49
    Microsoft
    0.48
     Bezos
    0.48
     Beatles
    0.44
    global
    0.44
     microsoft
    0.43
     Saudi
    0.43
    Activations Density 0.007%

    No Known Activations