Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2452
    Prev
    Next
    INDEX
    Explanations

    keywords and constructs related to programming and coding functions

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

    C# code: "public" keyword

    np_acts-logits-general · gemini-2.0-flash

    public followed by code declarations

    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
     automatiques
    -0.68
    AddTagHelper
    -0.66
     NDEBUG
    -0.64
     médicale
    -0.63
    transQ
    -0.61
     @"";
    -0.61
     butterknife
    -0.60
    PasswordEncoder
    -0.59
     médicaux
    -0.59
     Audiodateien
    -0.59
    POSITIVE LOGITS
     override
    0.84
     async
    0.77
    async
    0.57
     new
    0.54
     partial
    0.52
     virtual
    0.52
    override
    0.50
    virtual
    0.47
    delegate
    0.47
    %");
    0.45
    Activations Density 0.026%

    No Known Activations