© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3439
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and parameters related to phase differences in a scientific context

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

    the constant pi

    np_acts-logits-general · gemini-2.0-flash

    math expression involving pi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.74
    IntoConstraints
    -0.70
    delwed
    -0.56
     GoogleFonts
    -0.55
    WithIOException
    -0.54
     insuffisamment
    -0.53
     fieldNum
    -0.53
    
    -0.52
     JpaRepository
    -0.52
    AddTagHelper
    -0.52
    POSITIVE LOGITS
     π
    1.03
     pi
    0.94
    pi
    0.92
    π
    0.89
     PI
    0.75
     Pi
    0.74
    PI
    0.72
     pie
    0.68
    
    0.66
    𝜋
    0.65
    Activations Density 0.395%

    No Known Activations