© 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. 31523
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to ownership and operations, especially in the context of businesses or organizations

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

    legal, immigration, race, religion, or technical contexts

    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
    arrar
    -0.40
     doPost
    -0.30
     هم
    -0.29
     voraus
    -0.28
     egli
    -0.28
     evolução
    -0.28
    alerta
    -0.27
     прошла
    -0.27
     Kop
    -0.27
     mẫu
    -0.27
    POSITIVE LOGITS
     initComponents
    0.74
    providedIn
    0.71
    rungsseite
    0.70
    Personendaten
    0.67
     utafitiHapana
    0.67
     disambiguazione
    0.66
    хьтан
    0.65
     ſta
    0.63
    AddTagHelper
    0.62
     queſta
    0.61
    Activations Density 0.102%

    No Known Activations