© 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. 20-GEMMASCOPE-RES-16K
    11. 8875
    Prev
    Next
    INDEX
    Explanations

    elements related to coding functions and syntax in programming languages

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

    Python function declarations

    np_acts-logits-general · gemini-2.0-flash

    python function definitions

    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
     figure
    -0.55
     Suff
    -0.49
    <{
    -0.48
    ದು
    -0.48
    一部
    -0.48
    Suff
    -0.48
    kyou
    -0.47
    -//
    -0.46
    اتور
    -0.45
    fromnode
    -0.44
    POSITIVE LOGITS
    def
    1.91
     def
    1.37
     Def
    0.91
    Def
    0.88
     déf
    0.72
     deflection
    0.68
     DEF
    0.68
    ScopeManager
    0.67
     defence
    0.66
    CppMethod
    0.66
    Activations Density 0.044%

    No Known Activations