© 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. 1-GEMMASCOPE-RES-16K
    6. 14170
    Prev
    Next
    INDEX
    Explanations

    references to legal or formal applications and petitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.70
     snippetHide
    -0.68
     endforeach
    -0.67
     verrez
    -0.62
    forKey
    -0.62
    UVWXYZ
    -0.60
    resizingMask
    -0.59
     costuras
    -0.58
     raccont
    -0.57
    }{*}{
    -0.57
    POSITIVE LOGITS
     application
    4.78
     Application
    4.21
    application
    4.19
    Application
    4.00
     applications
    3.67
     APPLICATION
    3.64
    APPLICATION
    3.39
     Applications
    3.31
    applications
    3.17
    Applications
    3.08
    Activations Density 0.103%

    No Known Activations