© 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. 24-GEMMASCOPE-RES-16K
    6. 1106
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters in code or markup language contexts

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

    File paths and code snippets

    np_acts-logits-general · gemini-2.0-flash

    path components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    清楚
    -0.37
     siebie
    -0.37
     utilizarse
    -0.35
    地说道
    -0.34
     Chancen
    -0.34
     alcanzado
    -0.33
     griechischen
    -0.33
     Kooperation
    -0.32
    package
    -0.32
     chance
    -0.31
    POSITIVE LOGITS
    Tembelea
    0.82
    webElementXpaths
    0.81
    SequentialGroup
    0.72
    Vidite
    0.71
    ngdoc
    0.70
     незавершена
    0.67
     Italijanski
    0.67
     IFTT
    0.64
     typelib
    0.64
     <>",
    0.62
    Activations Density 0.853%

    No Known Activations