© 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. 2215
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal agreements and terms

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

    Prepositions followed by "terms" or "footing."

    np_acts-logits-general · gemini-2.0-flash

    on equal footing or terms

    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
    PasswordEncoder
    -0.62
     Fik
    -0.54
    condido
    -0.51
     Cité
    -0.49
    yorsunuz
    -0.46
     provinciale
    -0.45
     Vors
    -0.45
     zło
    -0.45
    colage
    -0.45
    setcounter
    -0.45
    POSITIVE LOGITS
     terms
    1.21
     Terms
    1.04
    terms
    1.01
    Terms
    1.00
     TERMS
    0.97
     termos
    0.90
     termes
    0.87
    TERMS
    0.86
     términos
    0.85
     conditions
    0.80
    Activations Density 0.189%

    No Known Activations