© 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. 2354
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss matters of importance or significance, particularly related to time and decision-making

    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
    ніципалі
    -0.79
    :✨
    -0.77
     ivelany
    -0.77
    Diwedd
    -0.75
    UnusedPrivate
    -0.72
    tagHelper
    -0.70
     nahilalakip
    -0.68
    OGND
    -0.67
     Roskov
    -0.66
    aarrggbb
    -0.66
    POSITIVE LOGITS
     matter
    1.27
    matter
    1.06
     questione
    1.05
     cuestión
    1.04
     question
    0.94
     questão
    0.92
     MATTER
    0.89
     matters
    0.87
    Matter
    0.79
     Matter
    0.78
    Activations Density 0.215%

    No Known Activations