© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4506
    Prev
    Next
    INDEX
    Explanations

    C++ template and class definitions, focusing on type specifications and structure templates

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

    C++ template declarations

    np_acts-logits-general · gemini-2.0-flash

    C++ template type parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kezés
    -0.36
    essler
    -0.36
    usakan
    -0.35
     Harus
    -0.35
     interviewing
    -0.34
     perusal
    -0.33
    govor
    -0.33
    katan
    -0.33
    acyjne
    -0.33
    говор
    -0.33
    POSITIVE LOGITS
    typeparam
    0.88
     '\\;'
    0.72
    تقاوى
    0.69
    MLLoader
    0.63
    səhifə
    0.61
    ViewFeatures
    0.58
    PyExc
    0.58
    awaiter
    0.57
     pinulongan
    0.56
    Portale
    0.56
    Activations Density 0.385%

    No Known Activations