© 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. 37-GEMMASCOPE-RES-16K
    11. 4508
    Prev
    Next
    INDEX
    Explanations

    structured data and coding conventions related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nine
    -0.42
     seven
    -0.41
     sixth
    -0.39
     eight
    -0.39
     six
    -0.39
     keempat
    -0.35
     seventh
    -0.35
     eighth
    -0.35
     Fifth
    -0.35
     tujuh
    -0.35
    POSITIVE LOGITS
     disambiguazione
    0.81
     betweenstory
    0.76
    ItemBackground
    0.75
    Personendaten
    0.68
    invokeLater
    0.66
    SourceChecksum
    0.66
    AddTagHelper
    0.64
    ReusableCell
    0.64
    AnimationsModule
    0.62
     مرئيه
    0.62
    Activations Density 1.409%

    No Known Activations