© 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. 59532
    Prev
    Next
    INDEX
    Explanations

    specific two to three-letter sequences or abbreviations that are often used in technical or scientific contexts

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

    -om/em endings

    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
    <h4>
    -0.70
    2
    -0.54
     tarda
    -0.54
     createSlice
    -0.53
    prefixer
    -0.52
    ा
    -0.52
     Volkes
    -0.52
    Спољашње
    -0.52
     Stö
    -0.50
     gracilis
    -0.49
    POSITIVE LOGITS
    m
    0.87
    im
    0.67
    tem
    0.65
    ym
    0.65
    م
    0.64
    AM
    0.62
    м
    0.62
     TPM
    0.61
    EM
    0.61
    TAM
    0.60
    Activations Density 0.222%

    No Known Activations