© 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. 20-GEMMASCOPE-RES-16K
    11. 16156
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming syntax

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

    Code snippets containing "return"

    np_acts-logits-general · gemini-2.0-flash

    formulation and dosage

    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
     nullptr
    -0.72
    nullptr
    -0.68
     incentiv
    -0.67
     onboarding
    -0.58
     ImGui
    -0.57
     samot
    -0.57
     foundational
    -0.57
     constexpr
    -0.57
    constexpr
    -0.55
     dédi
    -0.54
    POSITIVE LOGITS
     daß
    0.97
     muß
    0.89
     Daß
    0.78
    faßt
    0.75
     läßt
    0.72
    లాలు
    0.72
     Moslem
    0.70
     mußte
    0.70
     müßte
    0.69
    цездатний
    0.68
    Activations Density 0.561%

    No Known Activations