© 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. 31-GEMMASCOPE-RES-16K
    11. 10264
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts, specifically function definitions and method behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical explanations and code discussions in programming documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.78
     ſta
    -0.70
     ſur
    -0.65
    SharedCtor
    -0.65
    ſelf
    -0.63
     leaſt
    -0.61
    queryInterface
    -0.61
    ंदीखरीदारी
    -0.60
    QMetaType
    -0.60
     ***!
    -0.59
    POSITIVE LOGITS
     behaviour
    0.63
     comportement
    0.55
    <code>
    0.54
     explicitly
    0.54
     behavior
    0.52
     implicitly
    0.52
     behaviours
    0.51
     lazily
    0.48
     explicit
    0.47
     behaves
    0.47
    Activations Density 3.281%

    No Known Activations