© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11667
    Prev
    Next
    INDEX
    Explanations

    times and dates mentioned in the text

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

    Time abbreviations using "m" (a.m. / p.m.)

    np_acts-logits-general · gemini-2.0-flash

    times of day with am/pm

    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
     autorytatywna
    -1.03
     resourceCulture
    -0.86
    transQ
    -0.80
    出版年
    -0.72
     esternos
    -0.70
     gyhoeddwyd
    -0.70
    جغرافيا
    -0.67
     للاسماء
    -0.67
     kaarangay
    -0.67
    extAlignment
    -0.66
    POSITIVE LOGITS
     sharp
    0.86
     EST
    0.83
     ET
    0.78
     PST
    0.67
     EDT
    0.66
     CST
    0.64
    ET
    0.64
    sharp
    0.60
     SHARP
    0.59
     PDT
    0.57
    Activations Density 0.047%

    No Known Activations