© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14346
    Prev
    Next
    INDEX
    Explanations

    references to HIV and AIDS along with related medical services and interventions

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

    medical references to HIV/AIDS, with a focus on research, medical terminology, and specific details about the disease.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mentions of HIV/AIDS and closely related clinical, epidemiological, and treatment terminology.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    medical and scientific text related to HIV/AIDS research, treatment, and epidemiology.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    TargetException
    -0.44
    TypedValue
    -0.40
     teki
    -0.39
     بنت
    -0.38
     scrolls
    -0.37
    ValueGeneration
    -0.36
    ousa
    -0.36
    itiva
    -0.35
     فر
    -0.35
    pis
    -0.34
    POSITIVE LOGITS
     HIV
    0.94
    HIV
    0.87
    AIDS
    0.82
     AIDS
    0.82
     hiv
    0.68
     VIH
    0.65
    odeficiency
    0.63
     Aids
    0.60
    tagHelperRunner
    0.56
    Jeografia
    0.55
    Activations Density 0.281%

    No Known Activations