© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15680
    Prev
    Next
    INDEX
    Explanations

    phrases that express the capacity or ability to make something possible

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ￡
    -0.73
     الرياضيه
    -0.72
    govine
    -0.72
     grecque
    -0.72
    Bakgrunnsstoff
    -0.71
    heroku
    -0.71
    Wich
    -0.70
    ticals
    -0.69
    endaft
    -0.69
     asiatique
    -0.69
    POSITIVE LOGITS
     enable
    2.19
     enabling
    2.05
     Enable
    1.90
     enables
    1.83
     enabled
    1.68
     Enabling
    1.66
     Enables
    1.63
    enable
    1.59
    Enabling
    1.58
    Enable
    1.57
    Activations Density 0.097%

    No Known Activations