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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5881
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structure

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

    Code that declares or extends a class

    np_acts-logits-general · gemini-2.0-flash

    class definitions and inheritance

    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
    지를
    -0.49
     resolución
    -0.44
     por
    -0.44
     actuelles
    -0.43
    LayoutPanel
    -0.42
    rungsseite
    -0.42
     actuels
    -0.42
     resolution
    -0.41
    هات
    -0.41
     berper
    -0.41
    POSITIVE LOGITS
     nakalista
    0.98
     extends
    0.89
    extends
    0.88
     extending
    0.85
     extend
    0.80
     Extend
    0.78
    Personensuche
    0.77
     Extending
    0.73
    class
    0.72
     class
    0.71
    Activations Density 0.071%

    No Known Activations