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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5215
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming constructs and definitions of data types

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

    Code context, often involving "static" or "Tag"

    np_acts-logits-general · gemini-2.0-flash

    public static

    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
     originaux
    -0.67
    nologue
    -0.63
     propOrder
    -0.63
     mukana
    -0.60
    featureID
    -0.59
     Omen
    -0.58
     pasirink
    -0.56
    ymce
    -0.56
     trattano
    -0.55
     mineures
    -0.55
    POSITIVE LOGITS
     static
    0.89
    expandindo
    0.65
     initComponents
    0.63
    static
    0.61
     metastatic
    0.61
    Clik
    0.61
    __":
    
    0.56
    "]();
    0.56
     lateinit
    0.55
    ledo
    0.55
    Activations Density 0.028%

    No Known Activations