© 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. 1202
    Prev
    Next
    INDEX
    Explanations

    terms related to government, legislation, and regulatory matters

    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
     belong
    -0.60
    belong
    -0.58
     belonged
    -0.52
     trône
    -0.47
     belongs
    -0.47
    belongs
    -0.45
     regno
    -0.45
    來自
    -0.45
    ப்பட்டது
    -0.44
     reside
    -0.44
    POSITIVE LOGITS
     officials
    0.72
     decided
    0.64
     thinks
    0.62
     wants
    0.60
     expects
    0.59
    verifyException
    0.57
     intends
    0.57
     chose
    0.57
    BagConstraints
    0.56
     decides
    0.55
    Activations Density 0.855%

    No Known Activations