Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16372
    Prev
    Next
    INDEX
    Explanations

    references to programming namespaces and libraries

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

    C# using statements

    np_acts-logits-general · gemini-2.0-flash

    C# .NET namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    ⓧ
    -0.66
     Italijanski
    -0.54
     Италијани
    -0.47
    __:
    -0.45
    transQ
    -0.45
     кӀ
    -0.44
     surla
    -0.44
    saco
    -0.44
    -------------</
    -0.44
    COUVER
    -0.44
    POSITIVE LOGITS
     pouvoit
    0.56
     myſelf
    0.49
     colecciones
    0.49
     Komunikasi
    0.47
     feroit
    0.47
     sauvages
    0.46
     desmotivaciones
    0.46
     compagnies
    0.44
     vectorielles
    0.43
     royaume
    0.43
    Activations Density 0.006%

    No Known Activations