© 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. 22-GEMMASCOPE-RES-16K
    11. 14541
    Prev
    Next
    INDEX
    Explanations

    braces and their nesting levels in expressions

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

    LaTeX math mode

    np_acts-logits-general · gemini-2.0-flash

    mathematical functions and operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -1.06
     A
    -0.85
     is
    -0.84
    <eos>
    -0.84
     a
    -0.82
     the
    -0.82
    ,
    -0.82
     "
    -0.81
     del
    -0.80
     er
    -0.79
    POSITIVE LOGITS
     myſelf
    1.41
     itſelf
    1.37
     ſever
    1.34
     Majefty
    1.28
     faſt
    1.28
     photolibrary
    1.26
     Monfieur
    1.25
    ſelf
    1.24
     $_"
    1.24
     houſe
    1.23
    Activations Density 0.131%

    No Known Activations