© 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. 10-GEMMASCOPE-RES-16K
    11. 6041
    Prev
    Next
    INDEX
    Explanations

    events and conditions that evoke strong sensory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.65
     صفحۀ
    -0.63
    сылкі
    -0.61
     通販
    -0.60
    awtextra
    -0.59
    ConverterFactory
    -0.57
    InstrumentedTest
    -0.56
    
    -0.51
    ьаж
    -0.50
     ब्रेकडाउन
    -0.50
    POSITIVE LOGITS
    lickr
    0.39
    śl
    0.33
    flatMap
    0.32
    addEventListener
    0.30
    endswith
    0.30
     bureau
    0.29
     klok
    0.29
    ToFit
    0.29
     saksi
    0.28
     ACCORD
    0.28
    Activations Density 1.647%

    No Known Activations