© 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. 31-GEMMASCOPE-RES-131K
    11. 9213
    Prev
    Next
    INDEX
    Explanations

    assertions of belief and defense of principles related to freedom, rights, and the moral stance of individuals or groups in the context of historical and cultural discussions

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

    preserve the union

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.66
     disambiguazione
    -0.65
    новниш
    -0.60
     kaarangay
    -0.59
    webElementXpaths
    -0.56
     Signalez
    -0.56
     Numerade
    -0.56
    verifyException
    -0.54
    afficheront
    -0.53
    讓我們
    -0.53
    POSITIVE LOGITS
     möglichst
    0.45
    あくまで
    0.36
     pomocí
    0.35
     reject
    0.35
     rejection
    0.35
     betont
    0.35
     tramite
    0.34
    自分は
    0.34
     manual
    0.33
     massa
    0.33
    Activations Density 0.138%

    No Known Activations