© 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. 19-GEMMASCOPE-RES-16K
    6. 12024
    Prev
    Next
    INDEX
    Explanations

    statistics and demographic information related to populations and census data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.76
     transfieras
    -0.74
     ویکی‌پدیا
    -0.69
    UnknownFieldSet
    -0.64
     tartalomajánló
    -0.62
     חיצוניים
    -0.61
     ویکی‌پدی
    -0.60
    Geplaatst
    -0.58
     indisponible
    -0.57
     ujednoznacz
    -0.56
    POSITIVE LOGITS
     census
    1.57
     Census
    1.46
    Census
    1.26
    census
    1.12
     population
    1.09
     cens
    1.03
     Population
    1.00
    ENSUS
    0.98
    Population
    0.94
     demographic
    0.93
    Activations Density 0.177%

    No Known Activations