© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 59138
    Prev
    Next
    INDEX
    Explanations

    references to various medical disorders and conditions

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

    medical disorders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Мексичка
    -0.75
     îna
    -0.68
    bootstrapcdn
    -0.64
    thenReturn
    -0.62
     jspb
    -0.59
    ⓧ
    -0.57
    Lucas
    -0.54
    httphttps
    -0.54
    Leg
    -0.53
    GEBURTS
    -0.53
    POSITIVE LOGITS
     disorder
    0.87
     Disorder
    0.82
     disorders
    0.74
     Disorders
    0.73
     trastorno
    0.64
     trastornos
    0.60
    stornos
    0.58
     disordered
    0.53
    er
    0.46
     اختلال
    0.45
    Activations Density 0.020%

    No Known Activations