© 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. 24-GEMMASCOPE-RES-16K
    11. 1419
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to molecular biology and genetics

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

    Followed by single-letter protein mutations

    np_acts-logits-general · gemini-2.0-flash

    mutant proteins, double mutants, virus resistant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bienfaits
    -1.00
     vérit
    -0.82
     pouvoirs
    -0.81
     oreilles
    -0.81
     lèvres
    -0.81
     vœux
    -0.80
     dieux
    -0.80
     débats
    -0.79
     âmes
    -0.79
     négociations
    -0.79
    POSITIVE LOGITS
     systems
    0.96
     samples
    0.94
     specimens
    0.91
     populations
    0.83
     structures
    0.73
     tissues
    0.71
     members
    0.70
     individuals
    0.67
     objects
    0.66
     preparations
    0.66
    Activations Density 2.584%

    No Known Activations