© 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. 12939
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to problems and solutions

    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
     Māori
    -0.72
    iería
    -0.71
     članak
    -0.71
    oltà
    -0.70
    código
    -0.70
    portál
    -0.70
     cuánt
    -0.69
    éraire
    -0.69
    iläum
    -0.69
    ENCIÓN
    -0.69
    POSITIVE LOGITS
     isnt
    0.68
     wasnt
    0.67
     doesnt
    0.66
    Ã
    0.65
     didnt
    0.64
    �
    0.63
     Thats
    0.63
     thats
    0.62
     arent
    0.59
     __
    0.59
    Activations Density 0.421%

    No Known Activations