© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 9947
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to plastics and polymer production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сылкі
    -0.39
    aryen
    -0.39
    yakarta
    -0.38
     '\\;'
    -0.38
     ferru
    -0.38
    transQ
    -0.37
     kasarigan
    -0.37
     للمعارف
    -0.37
    SharedDtor
    -0.37
     prega
    -0.36
    POSITIVE LOGITS
     plastic
    1.70
     Plastic
    1.52
     plastics
    1.52
    plastic
    1.48
    Plastic
    1.47
     Plastics
    1.36
     PLASTIC
    1.33
    Plas
    1.28
    塑料
    1.25
     plastik
    1.24
    Activations Density 0.562%

    No Known Activations