© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2587
    Prev
    Next
    INDEX
    Explanations

    symptoms related to physical health conditions

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

    Symptoms of illness or disease

    np_acts-logits-general · gemini-2.0-flash

    medical symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    republik
    -0.57
    onAttach
    -0.57
     Mez
    -0.57
     ConstraintSet
    -0.57
    devamını
    -0.56
    WebElementEntity
    -0.55
    وق
    -0.54
     Anges
    -0.52
    มาะ
    -0.52
     foreseeable
    -0.51
    POSITIVE LOGITS
     difficulty
    0.84
     loss
    0.78
     decreased
    0.77
     increased
    0.76
    difficulty
    0.71
     Difficulty
    0.67
    Difficulty
    0.65
     difficoltà
    0.64
     frequent
    0.62
     Loss
    0.61
    Activations Density 0.485%

    No Known Activations