© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9084
    Prev
    Next
    INDEX
    Explanations

    statistical significance indicators in research data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.65
    AndEndTag
    -0.60
     للمعارف
    -0.59
    webElementGuid
    -0.58
     propOrder
    -0.57
     brigades
    -0.57
     للاسماء
    -0.57
    الحياه
    -0.57
    RectangleBorder
    -0.56
     modelAndView
    -0.56
    POSITIVE LOGITS
    XmlSchema
    0.39
     ayr
    0.36
    jspx
    0.34
     glede
    0.34
     competitive
    0.33
    beginPath
    0.32
     kuitenkin
    0.31
    bedarf
    0.31
     specifically
    0.31
     πάν
    0.30
    Activations Density 0.840%

    No Known Activations