© 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. 66048
    Prev
    Next
    INDEX
    Explanations

    specific diagnostic criteria and classification related to mental health disorders

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

    psychiatric disorders and treatments

    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
     للمعارف
    -0.45
    +#+#
    -0.40
    wanza
    -0.39
     penyel
    -0.38
    lihatan
    -0.38
     trap
    -0.37
     melay
    -0.35
     arasındaki
    -0.35
    Autoritní
    -0.35
     maș
    -0.35
    POSITIVE LOGITS
     psychiatrist
    0.73
     psychiatrists
    0.69
     Psychiatry
    0.67
     psychiatric
    0.66
     psychiatry
    0.65
     Psychiatric
    0.61
    Psychiat
    0.60
     antidepress
    0.59
     psiqui
    0.57
     psychotherapy
    0.57
    Activations Density 0.162%

    No Known Activations