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

    Neuronpedia

    Jacobian LensNEW
    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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15263
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to HIV/AIDS and its treatment

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

    HIV diagnosis and related studies

    np_acts-logits-general · gemini-2.0-flash

    HIV diagnosis disease

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    -0.46
    addPreferredGap
    -0.38
     mass
    -0.37
     teki
    -0.35
     Neb
    -0.34
     cyber
    -0.32
    bere
    -0.32
    berus
    -0.32
    TypedValue
    -0.31
    ValueGeneration
    -0.31
    POSITIVE LOGITS
     HIV
    0.91
    HIV
    0.82
    tagHelperRunner
    0.81
     AIDS
    0.76
    AIDS
    0.72
     hiv
    0.70
     VIH
    0.59
    odeficiency
    0.58
     Infórmanos
    0.56
    锈钢
    0.56
    Activations Density 0.626%

    No Known Activations