© 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. 6311
    Prev
    Next
    INDEX
    Explanations

    references to navigation elements and structure in web development

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

    HTML/JavaScript code structure elements like script tags, head tags, and other web development syntax.

    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
    WriteTagHelper
    -0.66
    ]")]
    -0.61
     Himo
    -0.59
    AddTagHelper
    -0.59
    MessageState
    -0.58
    httphttps
    -0.57
     Réponses
    -0.57
     <>",
    -0.56
    principalColumn
    -0.56
    createComponent
    -0.56
    POSITIVE LOGITS
     initComponents
    0.46
    JMenuBar
    0.39
    XtraBars
    0.34
     wear
    0.34
    ViewFeatures
    0.33
     instituciones
    0.32
     indoss
    0.32
    logout
    0.32
     header
    0.32
     otur
    0.31
    Activations Density 0.056%

    No Known Activations