© 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. 6544
    Prev
    Next
    INDEX
    Explanations

    information related to stability and storage systems

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

    preceding "storage"

    np_acts-logits-general · gemini-2.0-flash

    storage and storing items

    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
    __*/
    -0.56
     تضيفلها
    -0.56
    GEBURTSDATUM
    -0.55
    ofollow
    -0.54
    новниш
    -0.54
    findpost
    -0.53
     Савезне
    -0.52
    dymyr
    -0.52
     Jérusalem
    -0.51
    amaño
    -0.50
    POSITIVE LOGITS
     storage
    3.41
     Storage
    3.02
     storing
    2.91
    storage
    2.84
    Storage
    2.78
     STORAGE
    2.77
     stored
    2.72
     Storing
    2.54
    STORAGE
    2.49
    Storing
    2.45
    Activations Density 0.460%

    No Known Activations