© 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. 21-GEMMASCOPE-RES-16K
    11. 5846
    Prev
    Next
    INDEX
    Explanations

    punctuations and periods at the end of sentences

    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
     läßt
    -1.20
     muß
    -1.06
     definately
    -0.96
     müßte
    -0.94
     daß
    -0.91
     idéia
    -0.91
     mußte
    -0.88
     Daß
    -0.82
     skall
    -0.78
     Einfluß
    -0.78
    POSITIVE LOGITS
     “[
    0.99
    “[
    0.94
     Notably
    0.83
    Ahead
    0.82
     ⁠
    0.76
     prioritize
    0.76
     TikTok
    0.76
     prioritise
    0.75
    Alongside
    0.75
     Ahead
    0.75
    Activations Density 0.112%

    No Known Activations