© 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. 18496
    Prev
    Next
    INDEX
    Explanations

    occurrences of semicolons and other punctuation marks in code

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

    code and user input

    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
     nonUne
    -0.37
    VIAF
    -0.36
     Ka
    -0.34
    ẵn
    -0.32
     prisa
    -0.31
    はじめに
    -0.31
    <eos>
    -0.30
     Barbour
    -0.30
    UrlEncoded
    -0.29
     rü
    -0.29
    POSITIVE LOGITS
    SequentialGroup
    0.60
    Демографія
    0.55
    CloseOperation
    0.52
     fieldNum
    0.52
    jenige
    0.50
    tagHelperRunner
    0.50
    yntaxException
    0.50
    fjspx
    0.49
    RegressionTest
    0.49
    XmlRootElement
    0.48
    Activations Density 0.002%

    No Known Activations