© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 975
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes leading up to events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.73
     الحره
    -0.72
     disambiguazione
    -0.69
     مرئيه
    -0.69
    тьяна
    -0.69
    verwijspagina
    -0.68
    ThroughAttribute
    -0.67
    SBATCH
    -0.62
    rungsseite
    -0.61
     Waray
    -0.61
    POSITIVE LOGITS
     preceding
    0.70
     sebelum
    0.64
     before
    0.59
     preparation
    0.58
    BEFORE
    0.57
    Перед
    0.57
     culminating
    0.56
    before
    0.55
     ennen
    0.54
    Sebelum
    0.54
    Activations Density 0.257%

    No Known Activations