© 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. 40-GEMMASCOPE-RES-16K
    11. 5798
    Prev
    Next
    INDEX
    Explanations

    references to teaching and educational initiatives related to sewing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    newswire
    -0.44
    contentLoaded
    -0.44
    phosa
    -0.42
     ujednoznacz
    -0.42
    科学家
    -0.42
    astéro
    -0.41
    EDEFAULT
    -0.40
     textStatus
    -0.40
     мәкал
    -0.40
    出版年
    -0.40
    POSITIVE LOGITS
     lessons
    1.33
     Lessons
    1.16
     lesson
    1.13
    lessons
    1.07
    Lessons
    1.06
     classes
    1.06
     beginner
    1.05
     instructor
    1.05
     beginners
    1.02
     Beginners
    1.02
    Activations Density 0.204%

    No Known Activations