© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13779
    Prev
    Next
    INDEX
    Explanations

    terms related to legal rulings and judicial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.62
    ValueStyle
    -0.56
    ंदीखरीदारी
    -0.52
    +#+
    -0.49
    //
    -0.45
    Спољашње
    -0.44
    expandindo
    -0.43
    KommentareTeilen
    -0.41
     asumi
    -0.40
    saraba
    -0.39
    POSITIVE LOGITS
     hôtes
    0.42
     remanded
    0.42
    IActionResult
    0.40
    NewLabel
    0.39
     vectorielles
    0.38
    ISupport
    0.38
    EReference
    0.37
    SpringBootTest
    0.37
    verifyException
    0.36
     pères
    0.35
    Activations Density 2.401%

    No Known Activations