© 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 EvalsExportsinterp-engineNEWAPI 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. 77562
    Prev
    Next
    INDEX
    Explanations

    phrases related to integrity and fairness in various contexts

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

    fair dealing, bad audit

    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
     ujednoznacz
    -0.36
    empêcher
    -0.31
     tocado
    -0.29
     spécialement
    -0.28
     Verständ
    -0.28
     hell
    -0.28
     fine
    -0.27
     deportivas
    -0.27
     plegable
    -0.27
     Numerade
    -0.27
    POSITIVE LOGITS
    SequentialGroup
    0.71
    ########.
    0.65
    mobileqq
    0.61
    nonumber
    0.60
    ContentAsync
    0.56
     ब्रेकडाउन
    0.56
    Референце
    0.55
    
    0.54
    kuuta
    0.53
    extAlignment
    0.52
    Activations Density 0.081%

    No Known Activations