© 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. 8320
    Prev
    Next
    INDEX
    Explanations

    themes of uncertainty and change in personal experiences

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

    frequency or regularity

    np_acts-logits-general · gemini-2.0-flash

    frequently, often, regularly, constantly

    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
    tagHelperRunner
    -0.79
    GEBURTSDATUM
    -0.70
    原始内容存档于
    -0.69
     ModelExpression
    -0.69
     arşivlendi
    -0.68
    abestanden
    -0.67
    featureID
    -0.64
     Vikipedi
    -0.62
    первых
    -0.62
    saraba
    -0.61
    POSITIVE LOGITS
     frequently
    2.04
     regularly
    1.75
    frequently
    1.72
     often
    1.63
     frequentemente
    1.47
     Frequently
    1.45
     frecuentemente
    1.42
     constantly
    1.39
     fréquemment
    1.36
     frequent
    1.35
    Activations Density 0.357%

    No Known Activations