© 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. 4567
    Prev
    Next
    INDEX
    Explanations

    phrases and discussions relating to societal norms and regulations

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

    a period of time

    np_acts-logits-general · gemini-2.0-flash

    historically or since

    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
    RunAsync
    -0.76
     propOrder
    -0.72
     GenerationType
    -0.71
     елның
    -0.70
    ORAGE
    -0.66
    consulté
    -0.64
    bellar
    -0.63
    webElementXpaths
    -0.62
    INCREF
    -0.62
     cherchés
    -0.60
    POSITIVE LOGITS
     historically
    1.66
     since
    1.59
     Historically
    1.52
    Historically
    1.50
     decades
    1.46
     sejak
    1.46
    since
    1.41
    昔から
    1.39
     vroeger
    1.37
     منذ
    1.36
    Activations Density 1.294%

    No Known Activations