© 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. 13763
    Prev
    Next
    INDEX
    Explanations

    instances of code structure and class definitions in programming documents

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

    Java access modifiers (private, static, public)

    np_acts-logits-general · gemini-2.0-flash

    private keywords

    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
     DBNull
    -0.73
     MotionEvent
    -0.73
    WebVitals
    -0.70
    NgModule
    -0.70
     CGSize
    -0.69
     LoginComponent
    -0.63
     NgModule
    -0.62
    stdc
    -0.62
    Gambas
    -0.62
    preduce
    -0.62
    POSITIVE LOGITS
    private
    1.25
     private
    1.00
     static
    0.92
    public
    0.87
    static
    0.85
    protected
    0.80
     int
    0.72
     public
    0.71
     Private
    0.70
     final
    0.69
    Activations Density 0.058%

    No Known Activations