© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 38426
    Prev
    Next
    INDEX
    Explanations

    keywords and symbols related to programming constructs in code, particularly inheritance and class definitions

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

    class declaration and inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RegressionTest
    -0.79
     nonUne
    -0.63
    $_['
    -0.60
     resourceCulture
    -0.57
     <=",
    -0.56
     متعلقه
    -0.54
    ⟬
    -0.54
     '\\;'
    -0.53
     <>",
    -0.53
    aarrggbb
    -0.53
    POSITIVE LOGITS
    dengar
    0.41
    extends
    0.38
     Radford
    0.35
    EClass
    0.35
    prototype
    0.34
     extension
    0.33
     base
    0.33
     universal
    0.33
     Academy
    0.33
    behavior
    0.33
    Activations Density 0.026%

    No Known Activations