© 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. 20-GEMMASCOPE-RES-16K
    11. 8839
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical parameters and functions in a technical context

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

    Greek letters and mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    Greek letters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.63
     myſelf
    -0.62
     itſelf
    -0.61
     purpoſe
    -0.60
    ttemberg
    -0.58
    ſelf
    -0.57
     coar
    -0.57
     preſent
    -0.57
     Houſe
    -0.56
     pleaſure
    -0.56
    POSITIVE LOGITS
     alpha
    1.36
     Alpha
    1.26
     beta
    1.21
    alpha
    1.21
     Beta
    1.15
    Alpha
    1.13
     theta
    1.12
     Theta
    1.12
     Omega
    1.10
     omega
    1.09
    Activations Density 1.349%

    No Known Activations