© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions or pathologies involving changes in tissue structure or morphology

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

    Pathological changes or impairments

    np_acts-logits-general · gemini-2.0-flash

    pathological changes and dysfunction

    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
    PhysRev
    -0.67
     tetanus
    -0.54
    ILayout
    -0.53
    Interop
    -0.53
     Rape
    -0.52
     Antibiotics
    -0.52
     tweezers
    -0.52
    Sucesor
    -0.51
    Hochspringen
    -0.50
    uteen
    -0.49
    POSITIVE LOGITS
     alterations
    1.04
     abnormal
    0.96
     altered
    0.94
     changes
    0.93
     abnormalities
    0.93
     alteration
    0.91
     abnormality
    0.88
     damage
    0.86
     impaired
    0.80
     dysfunction
    0.80
    Activations Density 2.131%

    No Known Activations