Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11768
    Prev
    Next
    INDEX
    Explanations

    elements and attributes from markup or code snippets, particularly focusing on HTML and XML syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createSlice
    -0.56
     WaitForSeconds
    -0.49
    TypedDataSet
    -0.45
    StartCoroutine
    -0.45
     actionMode
    -0.44
    transQ
    -0.42
     Baile
    -0.41
     queſta
    -0.41
    astify
    -0.40
    ंदीखरीदारी
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
    XmlAttribute
    0.64
    WriteAttribute
    0.55
    HtmlAttribute
    0.53
    AddHtmlAttribute
    0.47
     ivelany
    0.46
    classnames
    0.45
     autorytatywna
    0.45
    тьяна
    0.45
    removeAttr
    0.44
    Activations Density 0.430%

    No Known Activations