© 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-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6985
    Prev
    Next
    INDEX
    Explanations

    indicators of numerical values and fiscal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.84
    awtextra
    -0.78
    ρών
    -0.74
    XmlAccessType
    -0.72
     ElementRef
    -0.71
    IntoConstraints
    -0.70
     PopupWindow
    -0.69
    engertian
    -0.68
     }</
    -0.67
    extAlignment
    -0.65
    POSITIVE LOGITS
    TagMode
    0.77
     utafitiHapana
    0.62
     year
    0.56
    year
    0.55
     letech
    0.55
    /******/
    0.54
     years
    0.52
    vum
    0.52
    years
    0.51
     årene
    0.50
    Activations Density 0.055%

    No Known Activations