© 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 EvalsExportsinterp-engineNEWAPI 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. 16270
    Prev
    Next
    INDEX
    Explanations

    specific biological terms and conditions related to molecular biology and virology

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

    Non-English language fragments or symbols

    np_acts-logits-general · gemini-2.0-flash

    Romanian, French, or academic text fragments

    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
     Monfieur
    -1.63
     myſelf
    -1.62
     Reſ
    -1.57
     Anſ
    -1.56
     raiſ
    -1.55
     purpoſe
    -1.53
     itſelf
    -1.53
     Diſ
    -1.53
     Efq
    -1.50
     Eſ
    -1.48
    POSITIVE LOGITS
     „
    0.65
     de
    0.57
     la
    0.56
     et
    0.53
     o
    0.51
    -
    0.49
     na
    0.47
    ,
    0.47
     i
    0.47
     ist
    0.47
    Activations Density 0.009%

    No Known Activations