© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4379
    Prev
    Next
    INDEX
    Explanations

    references to different classes or categorizations in a variety of contexts

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

    "class" or "classes"

    np_acts-logits-general · gemini-2.0-flash

    class / classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bandeira
    -0.56
     noDo
    -0.56
    OGND
    -0.54
    Conteúdo
    -0.53
     iluminação
    -0.52
     voedsel
    -0.49
     חיצוניים
    -0.48
     maquiagem
    -0.47
    mentação
    -0.47
     galinha
    -0.47
    POSITIVE LOGITS
     Class
    1.07
     CLASS
    0.94
    Class
    0.92
    CLASS
    0.84
    class
    0.83
     class
    0.82
     classe
    0.81
     Classe
    0.81
     Classes
    0.76
    classe
    0.74
    Activations Density 0.156%

    No Known Activations