© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs related to control flow in code

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

    Code snippets

    np_acts-logits-general · gemini-2.0-flash

    code and technical terms

    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
    Datuak
    -0.75
     فريبيس
    -0.71
    TagMode
    -0.68
    TagHelper
    -0.67
    principalTable
    -0.67
    Попис
    -0.66
     ErrIntOverflow
    -0.62
    StoryboardSegue
    -0.61
    PreferredItem
    -0.61
     Exacts
    -0.60
    POSITIVE LOGITS
     autorytatywna
    0.49
    igslist
    0.49
     then
    0.48
    illère
    0.48
     yoksa
    0.47
     então
    0.46
    phosa
    0.46
     {
    0.45
     entonces
    0.45
     alors
    0.45
    Activations Density 0.028%

    No Known Activations