© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 15760
    Prev
    Next
    INDEX
    Explanations

    references to events or situations related to emergencies or lockdowns during the COVID-19 pandemic

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    curfews or lockdowns

    np_acts-logits-general · gemini-2.0-flash

    lockdown and curfew

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    WebElementEntity
    -0.60
    InputTagHelper
    -0.57
    tagHelperRunner
    -0.54
    ReusableCell
    -0.54
    SequentialGroup
    -0.54
    hamilan
    -0.47
    RegressionTest
    -0.46
    GTCX
    -0.45
     häls
    -0.45
    httphttps
    -0.44
    POSITIVE LOGITS
     lockdown
    1.53
     lock
    1.33
     lockdowns
    1.30
     Lockdown
    1.29
    lock
    1.17
     LOCK
    1.16
     Lock
    1.11
     locking
    1.08
    Lock
    1.07
     locks
    1.03
    Activations Density 0.063%

    No Known Activations