© 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 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. 81053
    Prev
    Next
    INDEX
    Explanations

    elements of negativity or dismissal in the text

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

    non-English & punctuation

    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
     ProtoMessage
    -0.79
    rungsseite
    -0.74
     дописавши
    -0.71
    GEBURTSDATUM
    -0.70
     otomatig
    -0.70
    hyrchwyd
    -0.69
     Normdatei
    -0.66
     Paglinawan
    -0.63
    Personendaten
    -0.63
    aarrggbb
    -0.62
    POSITIVE LOGITS
    KommentareTeilen
    0.39
    BeginInit
    0.37
    DoubleQuotes
    0.30
    scra
    0.30
     Pues
    0.30
    Ỹ
    0.29
     pecado
    0.28
    acade
    0.28
     Ensino
    0.28
    accro
    0.28
    Activations Density 0.072%

    No Known Activations