© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2443
    Prev
    Next
    INDEX
    Explanations

    the word "remember"

    oai_token-act-pair · gemini-2.0-flash

    remember

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remember
    -2.23
     remembering
    -2.06
     remembered
    -2.05
    remember
    -2.02
     Remember
    -2.00
     REMEMBER
    -1.97
     remembers
    -1.97
    Remember
    -1.89
     Remembering
    -1.70
     memory
    -1.67
    POSITIVE LOGITS
    Děkuji
    0.67
    Démographie
    0.66
    nestjs
    0.65
    twimg
    0.65
    AndroidJUnit
    0.63
     }}"></
    0.62
     venter
    0.61
    cassert
    0.60
     peindre
    0.60
    vedra
    0.59
    Activations Density 0.063%

    No Known Activations