© 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. 22-GEMMASCOPE-RES-16K
    11. 8308
    Prev
    Next
    INDEX
    Explanations

    personal experiences or emotional reactions related to childbirth or parenting

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

    Nausea, fainting, or feeling unwell

    np_acts-logits-general · gemini-2.0-flash

    physical distress or loss of consciousness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    раздо
    -0.56
    zionato
    -0.55
    SOUNDBITE
    -0.55
     innov
    -0.55
    auté
    -0.55
     CURIAM
    -0.54
     innovator
    -0.54
    IDENTAL
    -0.54
     étag
    -0.54
     AssemblyCompany
    -0.54
    POSITIVE LOGITS
     fainted
    1.19
     fainting
    1.13
     unconscious
    1.04
     puk
    0.96
     fain
    0.94
     vomiting
    0.93
     faint
    0.91
     vomit
    0.90
     vom
    0.89
     collapsed
    0.84
    Activations Density 0.281%

    No Known Activations