© 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. 45007
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of conceiving or designing projects and ideas

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

    conceived and designed

    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
     estadísticas
    -0.60
     armée
    -0.58
     autorité
    -0.56
     لينك
    -0.55
     lenker
    -0.54
    ʐ
    -0.54
    Rujuakan
    -0.54
     statistique
    -0.52
    ことなく
    -0.52
     alé
    -0.51
    POSITIVE LOGITS
     conception
    1.00
     conceive
    0.99
     conceived
    0.94
    conception
    0.93
     Conception
    0.91
    Conception
    0.83
     concep
    0.78
     concevoir
    0.74
     conceptions
    0.73
     concept
    0.73
    Activations Density 0.013%

    No Known Activations