© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 9243
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to cosmic microwave background (CMB) data and lensing in astrophysics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     idéia
    -1.11
    faßt
    -1.10
     daß
    -1.08
     muß
    -1.07
     läßt
    -0.86
     Einfluß
    -0.80
     definately
    -0.77
     mußte
    -0.76
     Schluß
    -0.73
     Moslem
    -0.73
    POSITIVE LOGITS
     impactful
    1.13
     microbiome
    1.07
     onboarding
    1.04
     Notably
    1.01
     incentiv
    1.00
     leveraging
    0.99
     nuanced
    0.96
     spatio
    0.88
     actionable
    0.86
    nullptr
    0.86
    Activations Density 5.715%

    No Known Activations