© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 847
    Prev
    Next
    INDEX
    Explanations

    occurrences and types of classes defined within programming or coding contexts

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

    The token "class" and related terms

    np_acts-logits-general · gemini-2.0-flash

    class

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     recuperação
    -0.45
    至於
    -0.43
    Tämä
    -0.43
     Pompeo
    -0.40
     ardından
    -0.40
     propOrder
    -0.40
     Moira
    -0.40
     SDLK
    -0.39
    they
    -0.39
    presumably
    -0.39
    POSITIVE LOGITS
     Class
    1.38
    Class
    1.37
     CLASS
    1.26
    class
    1.25
     class
    1.23
    CLASS
    1.16
     Classe
    1.09
     Classes
    1.08
     classe
    1.07
    Classes
    1.02
    Activations Density 0.116%

    No Known Activations