© 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. 20-GEMMASCOPE-RES-16K
    11. 3679
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude and appreciation

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

    Positive feedback/encouragement

    np_acts-logits-general · gemini-2.0-flash

    affirmation related to subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RectangleBorder
    -0.78
    IVAS
    -0.63
     StatelessWidget
    -0.62
    aarrggbb
    -0.61
     sqlalchemy
    -0.59
    adpleegd
    -0.58
    存于互联网档案馆
    -0.57
    bcrypt
    -0.56
     незавершена
    -0.56
    主な
    -0.56
    POSITIVE LOGITS
     deserves
    1.04
     truly
    1.00
     deserve
    0.99
     verkligen
    0.89
     Truly
    0.89
     virkelig
    0.88
    truly
    0.85
    Truly
    0.85
     really
    0.84
     verdaderamente
    0.82
    Activations Density 0.168%

    No Known Activations