© 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. 306
    Prev
    Next
    INDEX
    Explanations

    references to agreements or contracts between parties

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

    Signing or having an agreement/deal

    np_acts-logits-general · gemini-2.0-flash

    signed agreement or deal

    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
     NSCoder
    -0.56
     incomplète
    -0.54
    tagHelperRunner
    -0.54
     pinulongan
    -0.53
    issements
    -0.50
    principalTable
    -0.48
     referrerpolicy
    -0.48
     eingesetzt
    -0.47
    rítica
    -0.47
     opérés
    -0.47
    POSITIVE LOGITS
     agreement
    2.26
     agreements
    2.17
     Agreement
    1.94
     Agreements
    1.84
    agreement
    1.77
    Agreement
    1.74
     contract
    1.68
     AGREEMENT
    1.62
     agreed
    1.61
     contracts
    1.55
    Activations Density 0.412%

    No Known Activations