© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 119487
    Prev
    Next
    INDEX
    Explanations

    terms related to programming interfaces and class structures in Java

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

    Display, Email, Lunch, instruments

    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
    /**
    -0.33
    <?
    -0.26
    정
    -0.25
     jednost
    -0.25
    /**
    -0.24
    kehren
    -0.24
     perhaps
    -0.24
     gra
    -0.24
     bewegt
    -0.24
    //</
    -0.23
    POSITIVE LOGITS
    ſt
    0.69
     الرياضيه
    0.67
    GTCX
    0.66
    :✨
    0.65
     ChromeDriver
    0.63
     Waſſer
    0.59
     playmobil
    0.58
    GEBURTSDATUM
    0.57
     Commencez
    0.56
     Италијани
    0.56
    Activations Density 0.007%

    No Known Activations