© 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 EvalsExportsinterp-engineNEWAPI 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. 5838
    Prev
    Next
    INDEX
    Explanations

    terms related to distribution, licensing, and regulatory language

    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
     and
    -0.63
     propOrder
    -0.59
    richTextPanel
    -0.58
     ویکی‌پدی
    -0.57
    хьтан
    -0.57
     &
    -0.56
    性和
    -0.53
    rungsseite
    -0.53
    المناصب
    -0.53
    tinyos
    -0.49
    POSITIVE LOGITS
     alike
    1.05
     respectivamente
    0.77
     serta
    0.69
     respectively
    0.67
     sowie
    0.65
     zugleich
    0.60
     gleicher
    0.59
    sowie
    0.56
     соответственно
    0.52
     दोनों
    0.52
    Activations Density 1.367%

    No Known Activations