© 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. 21-GEMMASCOPE-RES-16K
    6. 7793
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies and visuals of the night sky

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.45
    WebVitals
    -0.45
    Footnotes
    -0.42
    eradish
    -0.41
     Weldon
    -0.40
    Uris
    -0.39
    gifter
    -0.39
    ValueStyle
    -0.38
    MigrationBuilder
    -0.38
    ಾಗಿ
    -0.38
    POSITIVE LOGITS
     sky
    2.17
     skies
    1.95
    sky
    1.62
     cielo
    1.61
     clouds
    1.59
     Skies
    1.58
     Sky
    1.56
     heavens
    1.56
    Sky
    1.52
     SKY
    1.51
    Activations Density 0.144%

    No Known Activations