© 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. 15873
    Prev
    Next
    INDEX
    Explanations

    coding syntax and logic patterns, particularly in programming or scripting contexts

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

    Code or math symbols

    np_acts-logits-general · gemini-2.0-flash

    amplitudes are inversely proportional

    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
    fjspx
    -0.85
     CreateTagHelper
    -0.77
    TagMode
    -0.66
    StoryboardSegue
    -0.66
     <",
    -0.65
    addCriterion
    -0.64
    LookAnd
    -0.64
    yaf
    -0.63
    PerformLayout
    -0.63
    SourceChecksum
    -0.63
    POSITIVE LOGITS
    (-
    0.68
    !=-
    0.63
     (-
    0.63
    ==-
    0.62
     -
    0.61
    =-
    0.61
    ADELPHIA
    0.57
     invokingState
    0.56
    >-
    0.55
     INVALID
    0.50
    Activations Density 0.159%

    No Known Activations