© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101477
    Prev
    Next
    INDEX
    Explanations

    variations of the word "how" in different languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     psychologie
    -0.48
     plancher
    -0.47
     littéraire
    -0.46
     giornal
    -0.46
     tutkim
    -0.46
     marbre
    -0.46
    JSONArray
    -0.46
     ledig
    -0.45
     tilbud
    -0.45
     doigt
    -0.44
    POSITIVE LOGITS
    Como
    0.91
     Como
    0.87
     como
    0.82
    como
    0.77
     COMO
    0.76
     comme
    0.73
    makeConstraints
    0.71
    Comme
    0.70
    comme
    0.70
     Comme
    0.69
    Activations Density 0.004%

    No Known Activations