© 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. 16-GEMMASCOPE-RES-16K
    11. 10357
    Prev
    Next
    INDEX
    Explanations

    references to environmental health issues and their implications

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

    followed by limiting adverbs like "only" or "solely."

    np_acts-logits-general · gemini-2.0-flash

    focus on specific conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     zelfs
    -0.48
    وفق
    -0.44
    removeAttr
    -0.44
     sekal
    -0.42
    webtoken
    -0.42
    posables
    -0.40
     même
    -0.40
     hatta
    -0.39
    人も
    -0.39
    bzero
    -0.38
    POSITIVE LOGITS
    あく
    0.95
     disambiguazione
    0.92
    あくまで
    0.85
    contentLoaded
    0.80
     solely
    0.77
     TextAppearance
    0.75
     primarily
    0.74
     only
    0.74
     exclusively
    0.73
    +#+#
    0.73
    Activations Density 0.590%

    No Known Activations