© 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. 30927
    Prev
    Next
    INDEX
    Explanations

    the presence of specific LaTeX commands related to document formatting

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

    German, French, and Spanish words

    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
     betweenstory
    -1.03
    الحياه
    -0.98
    IntoConstraints
    -0.90
     nakalista
    -0.86
    featureID
    -0.86
    ngrx
    -0.84
    GEBURTSDATUM
    -0.83
     queſta
    -0.83
    AnchorTagHelper
    -0.81
    InputBorder
    -0.81
    POSITIVE LOGITS
    usepackage
    0.52
    ]{
    0.40
     Braut
    0.30
     multifunctional
    0.27
    )}{
    0.27
     Bühne
    0.26
     Hayashi
    0.25
     loja
    0.24
    y
    0.24
     nuage
    0.24
    Activations Density 0.000%

    No Known Activations