© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 13951
    Prev
    Next
    INDEX
    Explanations

    references to academic or organizational domains, particularly URLs ending with specific suffixes like .edu, .gov, and .co

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HFILL
    -0.86
    rawDesc
    -0.83
    Brainz
    -0.78
    underland
    -0.75
     resourceCulture
    -0.71
    contentLoaded
    -0.70
    ViewFeatures
    -0.69
    INSEE
    -0.65
    msgid
    -0.65
    featureID
    -0.65
    POSITIVE LOGITS
    gov
    0.92
    ReusableCell
    0.72
    co
    0.70
    󠁢
    0.61
     Pelleg
    0.58
     gov
    0.57
    tfrac
    0.56
     متحده
    0.56
    GOV
    0.54
    Gov
    0.54
    Activations Density 0.103%

    No Known Activations