© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 6239
    Prev
    Next
    INDEX
    Explanations

    sentences that contain statements reflecting significant achievements or notable characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before descriptions

    np_acts-logits-general · gemini-2.0-flash

    creation and introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     есть
    -0.54
     Audiodateien
    -0.51
     there
    -0.50
    ようです
    -0.50
     некоторых
    -0.47
     depends
    -0.47
     some
    -0.46
    considerable
    -0.45
    有一
    -0.45
    dopodob
    -0.45
    POSITIVE LOGITS
     founded
    1.12
     designed
    1.07
     Designed
    1.02
     born
    1.02
     conceived
    1.02
     Featuring
    1.01
     Founded
    0.99
     Launched
    0.96
     Composed
    0.96
     launched
    0.95
    Activations Density 0.185%

    No Known Activations