© 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. 33-GEMMASCOPE-RES-16K
    11. 526
    Prev
    Next
    INDEX
    Explanations

    expressions related to quantities, measurements, and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.77
    GEBURTSDATUM
    -0.56
     betweenstory
    -0.52
    WriteTagHelper
    -0.51
     referenties
    -0.44
     BorderSide
    -0.43
    Kjelder
    -0.42
     متعلقه
    -0.39
     Kenn
    -0.39
    舺
    -0.39
    POSITIVE LOGITS
     càng
    1.35
    越
    1.30
    越是
    1.23
     desto
    1.13
     semakin
    1.11
    ยิ่ง
    1.07
     越
    1.05
     Чем
    1.00
    越多
    0.98
    越大
    0.95
    Activations Density 0.232%

    No Known Activations