© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 14408
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific metrics related to gene research and analysis

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     muß
    -1.42
     daß
    -1.33
     läßt
    -1.27
     müßte
    -1.21
     idéia
    -1.18
     mußte
    -1.08
     Moslem
    -1.07
     mußten
    -0.97
    faßt
    -0.97
     Daß
    -0.95
    POSITIVE LOGITS
     impactful
    1.15
     microbiome
    1.14
    TLDR
    1.10
     onboarding
    1.10
     curated
    1.08
    qPCR
    1.02
     incentiv
    1.00
     showcasing
    0.96
     vibe
    0.95
     overarching
    0.94
    Activations Density 3.913%

    No Known Activations