© 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. 20-GEMMASCOPE-RES-16K
    6. 4639
    Prev
    Next
    INDEX
    Explanations

    variations of the word "G" often used in informal contexts or greetings

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

    tokens and patterns in French or multilingual online chat conversations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.48
    ViewFeatures
    -0.47
     AssemblyTitle
    -0.46
     Wikimedijinoj
    -0.43
     cor
    -0.40
     equ
    -0.40
    存于互联网档案馆
    -0.39
    HtmlAttribute
    -0.38
     ec
    -0.38
     Department
    -0.38
    POSITIVE LOGITS
    
    0.54
    __(/*!
    0.52
    ViewImports
    0.51
    AndEndTag
    0.49
    ----</
    0.48
     Himo
    0.46
    mær
    0.46
    IVEREF
    0.45
    Vegeu
    0.44
    XmlAccessType
    0.44
    Activations Density 0.284%

    No Known Activations