© 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. 14893
    Prev
    Next
    INDEX
    Explanations

    information related to product announcements and updates

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

    Notifications or reminders

    np_acts-logits-general · gemini-2.0-flash

    upcoming events and new information

    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
    sizeCache
    -0.77
    principalColumn
    -0.72
    Zalety
    -0.63
    SuppressLint
    -0.62
    BagLayout
    -0.62
     مشارکت‌کنندگان
    -0.62
    AppMethodBeat
    -0.62
    XmlAccessorType
    -0.61
    SPATH
    -0.60
    PositiveButton
    -0.59
    POSITIVE LOGITS
    Upcoming
    1.15
     upcoming
    1.13
     Upcoming
    1.07
    Reminder
    1.03
    upcoming
    1.00
     reminder
    0.98
     Reminder
    0.93
     new
    0.92
    Reminders
    0.81
    reminder
    0.79
    Activations Density 0.191%

    No Known Activations