© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14685
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface features and user interactions

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

    Chinese characters

    np_acts-logits-general · gemini-2.0-flash

    connection information

    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
     Taktlose
    -0.50
    MLLoader
    -0.42
     Zähne
    -0.41
     correctes
    -0.40
     gué
    -0.39
    liefert
    -0.38
    GRect
    -0.38
     Hände
    -0.36
    uttosto
    -0.36
     Turquía
    -0.36
    POSITIVE LOGITS
     surla
    0.84
    ValueStyle
    0.77
     disambiguazione
    0.68
     transfieras
    0.66
     CreateTagHelper
    0.60
     Commencez
    0.57
     محفوظة
    0.56
    ographia
    0.55
    Hochspringen
    0.52
    GEBURTSDATUM
    0.52
    Activations Density 0.146%

    No Known Activations