© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 137
    Prev
    Next
    INDEX
    Explanations

    warnings and cautions related to health or safety

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

    Words/phrases related to "caution" or being careful

    np_acts-logits-general · gemini-2.0-flash

    use with caution or carefully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     nahilalakip
    -0.74
     незавершена
    -0.62
    Enllaces
    -0.55
     PyLong
    -0.54
     dương
    -0.53
    AddTagHelper
    -0.52
    itern
    -0.51
    KommentareTeilen
    -0.50
     SEDS
    -0.50
     linkovi
    -0.49
    POSITIVE LOGITS
     caution
    2.51
     Caution
    2.22
     careful
    2.11
     cautions
    2.04
     cautious
    2.03
    caution
    1.99
     beware
    1.94
    Caution
    1.93
     Careful
    1.86
     cautioned
    1.85
    Activations Density 0.456%

    No Known Activations