© 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. 16-GEMMASCOPE-RES-16K
    11. 4723
    Prev
    Next
    INDEX
    Explanations

    occurrences of access modifiers in code, specifically 'private', 'public', and 'protected'

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

    C++ or C# keywords

    np_acts-logits-general · gemini-2.0-flash

    programming keywords and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.72
     autorytatywna
    -0.70
    archiviato
    -0.68
    SizeMode
    -0.66
    peutic
    -0.65
    — 
    -0.65
    ">:
    -0.65
     فريبيس
    -0.65
     مرئيه
    -0.64
    )”
    -0.63
    POSITIVE LOGITS
    private
    1.00
    expandindo
    0.83
    public
    0.80
     private
    0.62
     public
    0.59
    ↵↵
    0.58
    protected
    0.53
    constructor
    0.49
    endregion
    0.49
    newInstance
    0.47
    Activations Density 0.035%

    No Known Activations