© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31923
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and health improvements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    words followed by specific completions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    -
    -0.44
     Affairs
    -0.43
     di
    -0.42
    ,
    -0.40
    र्थ
    -0.40
     minh
    -0.39
    opensource
    -0.39
    cer
    -0.38
     Ellis
    -0.38
    eria
    -0.37
    POSITIVE LOGITS
    Personendaten
    1.21
     utafitiHapana
    1.11
     kaarangay
    1.09
     ویکی‌پدی
    1.08
     Roskov
    1.07
    tagHelperRunner
    1.05
    kháu
    1.05
     سكانية
    1.04
     disambiguazione
    1.03
    StructEnd
    1.03
    Activations Density 0.162%

    No Known Activations