© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6142
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to programming and software functionalities

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

    Technical terms or code-related keywords

    np_acts-logits-general · gemini-2.0-flash

    command line and system tools

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    }{*}{}
    -0.36
    zumaki
    -0.31
    testng
    -0.29
    Cul
    -0.28
     reacción
    -0.28
     screen
    -0.28
    moduleId
    -0.27
     illustratie
    -0.27
    TagHelper
    -0.27
    Добрый
    -0.26
    POSITIVE LOGITS
    Билгалдахарш
    0.75
     AssemblyCulture
    0.74
    sidemargin
    0.68
    WebElementEntity
    0.66
    webElement
    0.66
     незавершена
    0.66
    Derbyniad
    0.61
    хьтан
    0.59
     الرياضيه
    0.59
    InjectAttribute
    0.58
    Activations Density 0.475%

    No Known Activations