Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3262
    Prev
    Next
    INDEX
    Explanations

    references to neurobiology and tau pathology in aging

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

    Abbreviations of scientific journals

    np_acts-logits-general · gemini-2.0-flash

    academic journal abbreviations

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    روض
    -0.51
    coroutines
    -0.49
     individuality
    -0.47
    ^
    -0.47
     lamen
    -0.45
     separately
    -0.45
     around
    -0.44
    jek
    -0.43
    こない
    -0.42
     administrative
    -0.42
    POSITIVE LOGITS
    Autoritní
    0.83
    出版年
    0.83
    省市镇
    0.76
     pinulongan
    0.76
    "){
    
    0.73
    CloseOperation
    0.72
    windowFixed
    0.72
    MemoryWarning
    0.71
    Personensuche
    0.71
    ModelAdmin
    0.69
    Activations Density 0.628%

    No Known Activations