© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 15896
    Prev
    Next
    INDEX
    Explanations

    code-related terms and definitions related to classes, functions, and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.63
     Bäume
    -0.48
     Tatsache
    -0.47
    SharedDtor
    -0.47
     Betracht
    -0.46
     çantası
    -0.46
    zunehmen
    -0.45
     Haushalt
    -0.44
    CppMethod
    -0.44
     comigo
    -0.44
    POSITIVE LOGITS
    ness
    0.79
    な
    0.59
    ly
    0.57
    ترین
    0.56
    LY
    0.54
    nessed
    0.54
    цездатний
    0.52
    NESS
    0.51
    ‌ترین
    0.51
     lizenzfreie
    0.49
    Activations Density 0.795%

    No Known Activations