© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14854
    Prev
    Next
    INDEX
    Explanations

    elements related to data aggregation and counting processes

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

    Counts, counting, duty cycles, and totals

    np_acts-logits-general · gemini-2.0-flash

    counting or displaying numbers

    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
     通販
    -0.49
     ActivatedRoute
    -0.49
     متعلقه
    -0.46
    \}^{
    -0.45
    XmlType
    -0.45
    :✨
    -0.45
     ویکی‌پدیا
    -0.44
    verwijspagina
    -0.43
     salaire
    -0.43
    Melhor
    -0.43
    POSITIVE LOGITS
     count
    1.91
    count
    1.69
     counts
    1.69
     counted
    1.69
     Count
    1.62
     counting
    1.58
    Count
    1.53
     COUNT
    1.52
    COUNT
    1.40
     Counts
    1.39
    Activations Density 0.427%

    No Known Activations