© 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. 11787
    Prev
    Next
    INDEX
    Explanations

    instructions and warnings related to medication and its administration

    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
     suitably
    -0.68
    følgelig
    -0.68
     ganske
    -0.59
    anggil
    -0.56
    ésultat
    -0.55
     entsprechend
    -0.54
    somewhat
    -0.54
    الإنجليزية
    -0.54
     variously
    -0.54
     correspondingly
    -0.53
    POSITIVE LOGITS
     unless
    1.33
    unless
    1.19
     unnecessarily
    1.15
    Unless
    1.06
     Unless
    1.00
     terlalu
    0.93
     слишком
    0.89
     too
    0.88
     quá
    0.87
     anything
    0.86
    Activations Density 0.568%

    No Known Activations