© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3198
    Prev
    Next
    INDEX
    Explanations

    terms related to neurodegenerative diseases and protein aggregation

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

    neurodegenerative diseases like ALS or Huntington's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    IsContent
    -0.61
     poveznice
    -0.54
    openConnection
    -0.51
     bébé
    -0.47
    iverr
    -0.45
     scuola
    -0.44
    ="../../
    -0.44
    ddots
    -0.43
    chte
    -0.43
     Evaluación
    -0.43
    POSITIVE LOGITS
     amyloid
    0.94
    rapie
    0.80
     Alzheimer
    0.76
    Alzheimer
    0.73
     pri
    0.71
    朊
    0.67
     protein
    0.66
     Dementia
    0.65
     aggregates
    0.65
    Goed
    0.64
    Activations Density 0.304%

    No Known Activations