© 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. 31-GEMMASCOPE-RES-131K
    11. 82146
    Prev
    Next
    INDEX
    Explanations

    references to public figures and their celebrity status

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

    famous, household, legend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     argint
    -0.47
    abstractmethod
    -0.46
    GTCX
    -0.43
    mainMenu
    -0.40
     désolés
    -0.40
    FunctionFlags
    -0.39
    Personensuche
    -0.39
    iornamento
    -0.39
     atve
    -0.37
     Democrá
    -0.37
    POSITIVE LOGITS
     famous
    0.90
     household
    0.84
     celebrity
    0.83
     celebrities
    0.79
    famous
    0.75
     recognizable
    0.74
     legend
    0.74
     celebridades
    0.72
    household
    0.71
     famoso
    0.68
    Activations Density 0.052%

    No Known Activations