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

    Neuronpedia

    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. 18-GEMMASCOPE-RES-16K
    11. 128
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly class and method declarations in object-oriented programming

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

    C++ virtual functions and methods

    np_acts-logits-general · gemini-2.0-flash

    method declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icksburg
    -0.55
    новниш
    -0.51
     cavallo
    -0.48
    JvmStatic
    -0.47
    quelize
    -0.47
     المعيارى
    -0.47
    ppon
    -0.45
    rayage
    -0.45
    didReceive
    -0.45
    AntiForgeryToken
    -0.44
    POSITIVE LOGITS
    ::~
    0.67
    EDEFAULT
    0.65
    IntoConstraints
    0.64
    abstractmethod
    0.62
    StoreMessageInfo
    0.61
    abstract
    0.57
    +#+
    0.57
     protected
    0.56
    #
    0.55
    fillType
    0.54
    Activations Density 0.241%

    No Known Activations