© 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. 9869
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts associated with court proceedings and compensation claims

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

    preceding "would have"

    np_acts-logits-general · gemini-2.0-flash

    hypothetical or counterfactual statements

    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
     Roskov
    -0.96
    EndGlobalSection
    -0.95
    parsedMessage
    -0.95
     nahilalakip
    -0.90
    contentLoaded
    -0.90
     propOrder
    -0.88
    IUrlHelper
    -0.85
     EconPapers
    -0.84
    клопе
    -0.83
    bootstrapcdn
    -0.81
    POSITIVE LOGITS
     would
    1.40
     hätte
    1.39
     hubiera
    1.30
    would
    1.25
     gdyby
    1.25
     aurait
    1.21
     auraient
    1.21
     Would
    1.18
     hätten
    1.17
     hubiese
    1.14
    Activations Density 0.709%

    No Known Activations