© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10318
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lesson" or its plural form "lessons."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wikipagina
    -0.41
     Angaben
    -0.39
     Angabe
    -0.37
     epä
    -0.36
     inhoud
    -0.35
     jopa
    -0.34
     sacerdotes
    -0.33
     stavu
    -0.33
     yder
    -0.33
     uzyskać
    -0.32
    POSITIVE LOGITS
     lesson
    2.98
     lessons
    2.84
     Lesson
    2.70
     Lessons
    2.58
    lesson
    2.58
    Lesson
    2.56
    lessons
    2.52
    Lessons
    2.47
     LESSON
    2.33
     leçon
    2.16
    Activations Density 0.102%

    No Known Activations