© 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. 5-GEMMASCOPE-RES-16K
    11. 12341
    Prev
    Next
    INDEX
    Explanations

    legal terms and contexts related to court cases and legal proceedings

    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
     surla
    -0.71
    …………………………………………
    -0.65
     дописавши
    -0.63
    ————————————————
    -0.53
    
    -0.53
    Diweddarwch
    -0.51
    ****************
    -0.47
    dientemente
    -0.47
     substanti
    -0.46
    ================
    -0.46
    POSITIVE LOGITS
    WriteTagHelper
    0.70
     BoxFit
    0.67
     mxArray
    0.65
    uitton
    0.61
     juridiques
    0.61
     getItemCount
    0.60
    createStatement
    0.60
    DebuggerNonUser
    0.59
    ']")
    0.59
    üyada
    0.59
    Activations Density 4.324%

    No Known Activations