© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11076
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and notations related to scientific equations

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

    Mathematical/physics symbols followed by operators/delimiters

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and assignments

    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
    bastien
    -0.55
     Márquez
    -0.55
    orrho
    -0.52
     Kirkpatrick
    -0.51
    AddHtmlAttribute
    -0.50
     Ibarra
    -0.46
    photobucket
    -0.43
    pores
    -0.42
     champagne
    -0.42
     Tahu
    -0.42
    POSITIVE LOGITS
     (-
    2.21
     $(-
    1.99
     negative
    1.99
    (-
    1.98
     Negative
    1.95
    =-
    1.95
    ,-
    1.95
     $=-
    1.90
    /-
    1.88
    Negative
    1.85
    Activations Density 2.377%

    No Known Activations