© 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. 18-GEMMASCOPE-RES-16K
    11. 1890
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical diagnostics and healthcare

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

    Code, symbols, and foreign characters

    np_acts-logits-general · gemini-2.0-flash

    prosecutorial misconduct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dersfield
    -0.95
    に
    -0.93
    ology
    -0.92
    ly
    -0.86
    出版年
    -0.85
    tagext
    -0.75
    arithmic
    -0.74
     Lawton
    -0.74
    MigrationBuilder
    -0.74
    ised
    -0.74
    POSITIVE LOGITS
    й
    1.14
    ン
    0.99
    ers
    0.87
    一个
    0.81
    ι
    0.80
    йки
    0.79
    __*/
    0.77
     squee
    0.75
    к
    0.72
    pejo
    0.72
    Activations Density 1.038%

    No Known Activations