© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 27651
    Prev
    Next
    INDEX
    Explanations

    terms related to the deterioration of health or worsening conditions

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

    deterioration, aggravation, or worsening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     zwiſchen
    -0.64
    Tembelea
    -0.63
    ロウィン
    -0.63
    ﹧
    -0.61
    zaSy
    -0.61
    })`
    -0.60
    ReusableCell
    -0.59
    нгред
    -0.59
    rungsseite
    -0.59
     tartalo
    -0.59
    POSITIVE LOGITS
     worsen
    1.55
     worsening
    1.54
     worsened
    1.49
    wors
    1.05
     Wors
    1.03
    worse
    0.99
     wors
    0.98
     worse
    0.97
    Worse
    0.94
     Worse
    0.93
    Activations Density 0.014%

    No Known Activations