© 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 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. 93400
    Prev
    Next
    INDEX
    Explanations

    instances of the word "new."

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

    new, nuevo, 新的, ใหม่

    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
     queſta
    -0.89
     المعيارى
    -0.77
     tartalomajánló
    -0.77
    /**
    -0.75
    Tembelea
    -0.70
    ptonshire
    -0.69
    ésultats
    -0.68
    ſehen
    -0.67
    /*
    -0.67
    bootstrapcdn
    -0.66
    POSITIVE LOGITS
    new
    0.99
     new
    0.96
     New
    0.83
    New
    0.79
    NEW
    0.65
     NEW
    0.64
     Nuevo
    0.63
    新的
    0.59
     neuen
    0.57
    ใหม่
    0.57
    Activations Density 0.002%

    No Known Activations