© 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. 81059
    Prev
    Next
    INDEX
    Explanations

    references to interior spaces or elements related to interior design

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

    describing tangible interiors

    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
    Bundes
    -0.69
     bershka
    -0.69
     informée
    -0.68
     Inscrivez
    -0.68
    KommentareTeilen
    -0.67
    snail
    -0.67
    ambién
    -0.66
    expandindo
    -0.63
     Boltzmann
    -0.62
     Wikipédia
    -0.61
    POSITIVE LOGITS
     interior
    0.73
     Interior
    0.72
    Interior
    0.68
    INTERIOR
    0.66
    interior
    0.66
     interiores
    0.64
     INTERIOR
    0.63
     exterior
    0.60
     interiors
    0.57
    ior
    0.54
    Activations Density 0.006%

    No Known Activations