© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 97005
    Prev
    Next
    INDEX
    Explanations

    instances of braces and brackets in the text

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

    mathematical fractions

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Италијани
    -0.93
    parsedMessage
    -0.85
    CloseOperation
    -0.81
     Roskov
    -0.76
    IntoConstraints
    -0.74
    şört
    -0.70
    UserScript
    -0.70
     AssemblyCulture
    -0.68
    ьаж
    -0.68
    
    -0.68
    POSITIVE LOGITS
    section
    0.56
    Section
    0.50
    Primary
    0.44
    Chapter
    0.43
    }{*}{
    0.43
    <h2>
    0.41
    {
    0.41
    item
    0.40
    IN
    0.39
     "
    0.38
    Activations Density 0.011%

    No Known Activations