© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6539
    Prev
    Next
    INDEX
    Explanations

    key concepts related to molecular structure and dynamics in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.49
    rrggbb
    -0.45
     Nutrients
    -0.45
     surla
    -0.44
     Antic
    -0.44
     Antibodies
    -0.43
     Antimicrobial
    -0.43
    berglass
    -0.43
     Circular
    -0.42
    Comida
    -0.42
    POSITIVE LOGITS
     physics
    0.98
     physical
    0.97
    physical
    0.82
     phenomena
    0.79
    physics
    0.78
     behaviour
    0.77
     behavior
    0.77
     phys
    0.74
     physic
    0.73
     properties
    0.72
    Activations Density 1.830%

    No Known Activations