© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14236
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific terms related to genetics and virology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kaufman
    -0.72
     Glaser
    -0.70
     Schen
    -0.60
     McLaughlin
    -0.60
     jäsen
    -0.59
     Metcalf
    -0.58
     Nagel
    -0.58
     Rubin
    -0.58
     Shapiro
    -0.57
     Conley
    -0.56
    POSITIVE LOGITS
     CCC
    1.45
     SSS
    1.37
     GG
    1.36
     PPP
    1.35
     MMM
    1.35
     KK
    1.34
     kk
    1.32
     SS
    1.30
     BBB
    1.30
     DD
    1.29
    Activations Density 2.729%

    No Known Activations