© 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. 3-GEMMASCOPE-RES-16K
    11. 10621
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptors related to filtering and library functions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Chriſt
    -0.82
    ergies
    -0.77
     Monfieur
    -0.77
     tagName
    -0.73
     preſent
    -0.71
     PhpStorm
    -0.71
     theſe
    -0.70
     Moby
    -0.69
    safari
    -0.69
     Hymen
    -0.69
    POSITIVE LOGITS
     ft
    1.34
    ft
    1.28
    FT
    1.14
     FT
    1.11
     Arc
    0.87
     Ft
    0.85
    Ft
    0.82
     arc
    0.82
    fta
    0.81
    Arc
    0.79
    Activations Density 0.135%

    No Known Activations