© 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. 38-GEMMASCOPE-RES-16K
    11. 13256
    Prev
    Next
    INDEX
    Explanations

    terms associated with physical interactions in scientific contexts, particularly in relation to active matter and particle dynamics

    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
     maybe
    -0.49
     perhaps
    -0.48
     Table
    -0.48
     somehow
    -0.48
     obviously
    -0.47
     anyways
    -0.47
    obviously
    -0.46
    Anyway
    -0.45
     anyway
    -0.45
     Figure
    -0.44
    POSITIVE LOGITS
     demonstrate
    0.66
     demonstrates
    0.65
     novel
    0.65
     erstmals
    0.63
    rungsseite
    0.60
     впервые
    0.59
     demonstrating
    0.58
    novel
    0.56
    实现了
    0.56
     föres
    0.56
    Activations Density 2.348%

    No Known Activations