© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3922
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly in a legal or scientific context

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

    Numbers within court cases and time stamps

    np_acts-logits-general · gemini-2.0-flash

    timestamps and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     previous
    -1.00
    Previous
    -0.82
    PREVIOUS
    -0.81
     PREVIOUS
    -0.81
     Previous
    -0.79
     sebelumnya
    -0.77
    previous
    -0.76
     предыду
    -0.74
     preceding
    -0.71
     earlier
    -0.70
    POSITIVE LOGITS
    abestanden
    0.56
     disambiguazione
    0.54
     getItemId
    0.52
     noDo
    0.50
    ніципалі
    0.49
    FXML
    0.49
     suiv
    0.49
    JsonFormat
    0.48
     ffilmiau
    0.48
     suivez
    0.47
    Activations Density 0.429%

    No Known Activations