© 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. 10738
    Prev
    Next
    INDEX
    Explanations

    references to non-volatile memory and its characteristics

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

    Saving or storing data/preferences

    np_acts-logits-general · gemini-2.0-flash

    saves and stores data

    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
    PyExc
    -0.57
    SequentialGroup
    -0.55
    WaitGroup
    -0.50
    ̍t
    -0.48
     vermelhas
    -0.48
     Jezus
    -0.47
    ército
    -0.47
     Accesat
    -0.47
    faker
    -0.46
    Descriere
    -0.45
    POSITIVE LOGITS
     saved
    1.23
     save
    1.19
     stored
    1.17
     storage
    1.13
     saves
    1.12
     storing
    1.12
     Save
    1.11
     saving
    1.08
     Storage
    1.04
    Save
    1.02
    Activations Density 0.550%

    No Known Activations