© 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. 105890
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical and statistical analysis within text

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

    methods and alternatives

    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
     للاسماء
    -0.78
     HttpNotFound
    -0.67
    IntoConstraints
    -0.62
    parsedMessage
    -0.61
    setVerticalGroup
    -0.59
    EReference
    -0.59
     للمعارف
    -0.56
    PYX
    -0.55
     Wikimedijinoj
    -0.53
    RTEX
    -0.53
    POSITIVE LOGITS
     alternative
    0.40
     recommandée
    0.39
    alternative
    0.35
     alternativo
    0.34
     methods
    0.34
    Methods
    0.34
    methode
    0.33
     different
    0.32
     resolution
    0.32
     метод
    0.32
    Activations Density 0.082%

    No Known Activations