© 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. 0-GEMMASCOPE-RES-16K
    11. 9487
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "annular" in the context of lipid binding and its implications for channel functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.54
     ویکی‌پدی
    -0.54
     estekak
    -0.54
    NameInMap
    -0.52
    出版年
    -0.51
     propOrder
    -0.51
    inSlope
    -0.50
    Parcelize
    -0.50
     betweenstory
    -0.50
     intptr
    -0.49
    POSITIVE LOGITS
     conceptual
    0.79
     Conceptual
    0.69
    Conceptual
    0.69
     conceptu
    0.56
    conceptual
    0.54
     conceived
    0.53
     conceptually
    0.50
    Concept
    0.48
     conceive
    0.46
     complimentary
    0.46
    Activations Density 0.214%

    No Known Activations