© 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. 18-GEMMASCOPE-RES-16K
    11. 14812
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to rights, waiver, and procedural requirements in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text relating to compliance or requirements

    np_acts-logits-general · gemini-2.0-flash

    legal context, rules, compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.63
     gon
    -0.57
    Dip
    -0.51
    mis
    -0.51
    joc
    -0.51
    negan
    -0.49
    abestanden
    -0.49
    dymyr
    -0.49
    جاه
    -0.48
    ус
    -0.47
    POSITIVE LOGITS
     pursuant
    1.22
     according
    1.17
     enligt
    1.08
     accordance
    1.00
     согласно
    0.96
    according
    0.95
     conformément
    0.94
     según
    0.93
     gemäß
    0.93
     sebagaimana
    0.91
    Activations Density 1.306%

    No Known Activations