© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10014
    Prev
    Next
    INDEX
    Explanations

    specific patterns or structures related to code, such as variable declarations and class definitions in programming

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

    "public" in code

    np_acts-logits-general · gemini-2.0-flash

    public keyword

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.90
     Roskov
    -0.79
    клопе
    -0.67
     beginnetje
    -0.65
    はじめに
    -0.65
    SourceChecksum
    -0.65
     typelib
    -0.65
    Manbalar
    -0.64
    كويكب
    -0.62
     Paglinawan
    -0.61
    POSITIVE LOGITS
    public
    2.24
     public
    1.86
     público
    1.10
     pública
    1.05
    Public
    1.00
     publics
    0.96
     PUBLIC
    0.96
     Public
    0.94
     publice
    0.93
     pubblica
    0.91
    Activations Density 0.060%

    No Known Activations