© 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. 4-GEMMASCOPE-RES-16K
    11. 216
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and judicial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.56
    BeginContext
    -0.53
    AdapterView
    -0.51
    AddTagHelper
    -0.51
    copyWith
    -0.50
    Subview
    -0.48
    rucks
    -0.48
    arParams
    -0.48
     catch
    -0.48
    paramref
    -0.48
    POSITIVE LOGITS
     Ombudsman
    0.91
     omb
    0.82
     Auditor
    0.75
     auditor
    0.70
     Omb
    0.69
     auditing
    0.67
     audit
    0.67
     auditors
    0.66
    udsman
    0.66
     inquest
    0.65
    Activations Density 1.216%

    No Known Activations