© 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. 11213
    Prev
    Next
    INDEX
    Explanations

    references to graduation-related events and displays

    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
    XmlAccessorType
    -0.39
    หลวง
    -0.39
     room
    -0.39
    Lähteet
    -0.38
    sstelle
    -0.37
     Saal
    -0.35
    病房
    -0.34
    Дереккөздер
    -0.33
    会場
    -0.33
     tafel
    -0.32
    POSITIVE LOGITS
     lawn
    1.40
     backyard
    1.37
     yard
    1.33
     driveway
    1.33
    Lawn
    1.22
     neighbors
    1.20
     garden
    1.17
     lawns
    1.17
     neighbor
    1.16
     Lawn
    1.16
    Activations Density 0.279%

    No Known Activations