© 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. 12276
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evaluative judgments about concepts, particularly in the context of drug delivery and social commentary

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

    positive sentiment

    np_acts-logits-general · gemini-2.0-flash

    positive or negative sentiment

    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
    énario
    -0.60
    jsonwebtoken
    -0.54
    出版年
    -0.48
    клопе
    -0.48
    Solución
    -0.48
     springfox
    -0.48
    /**
    -0.46
    ]<<
    -0.46
    σμα
    -0.46
    <!--[
    -0.46
    POSITIVE LOGITS
     positive
    2.25
    positive
    2.04
     Positive
    1.95
     positively
    1.93
    Positive
    1.92
     POSITIVE
    1.91
     positives
    1.86
     negative
    1.84
     positif
    1.83
     Negative
    1.66
    Activations Density 0.489%

    No Known Activations