© 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. 15853
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or evaluations between different methods, materials, or scenarios

    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
     GenerationType
    -0.66
    brigens
    -0.63
    setVerticalGroup
    -0.61
    argout
    -0.60
    ddots
    -0.58
    WriteBarrier
    -0.58
    SuppressMessage
    -0.56
    AntiForgeryToken
    -0.55
    wpdb
    -0.55
    czegó
    -0.55
    POSITIVE LOGITS
     conventional
    2.71
     normal
    2.66
     traditional
    2.60
     usual
    2.58
     ordinary
    2.53
    traditional
    2.31
     regular
    2.30
    normal
    2.29
     typical
    2.29
    usual
    2.28
    Activations Density 1.824%

    No Known Activations