© 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 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. 1186
    Prev
    Next
    INDEX
    Explanations

    mentions of equations, particularly focusing on their states and numbering

    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
     nahilalakip
    -0.83
    NameInMap
    -0.71
    */
    -0.67
    #![
    -0.66
     HttpNotFound
    -0.65
    NOSTIC
    -0.65
    verständlich
    -0.64
    StructEnd
    -0.64
    RUnlock
    -0.63
    IBar
    -0.62
    POSITIVE LOGITS
     equation
    3.02
     equations
    2.84
     Equation
    2.51
     Equations
    2.48
    equation
    2.43
    Equation
    2.42
    equations
    2.38
    Equations
    2.33
    équation
    1.62
     eqn
    1.42
    Activations Density 0.188%

    No Known Activations