© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101404
    Prev
    Next
    INDEX
    Explanations

    the word "top" in various contexts indicating ranking or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    하였다
    -0.39
     Balkon
    -0.38
     construção
    -0.37
     છે
    -0.36
     skriver
    -0.36
     Durée
    -0.36
    icleta
    -0.35
    proses
    -0.35
     passagem
    -0.35
     זאת
    -0.34
    POSITIVE LOGITS
     top
    0.96
     Top
    0.81
     TOP
    0.77
    getTop
    0.77
     leaſt
    0.74
    Top
    0.71
     highest
    0.65
     best
    0.65
     beſt
    0.65
     टॉप
    0.64
    Activations Density 0.013%

    No Known Activations