© 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. 8995
    Prev
    Next
    INDEX
    Explanations

    verbs associated with conducting studies, analyses, or business activities

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

    the word "conduct"

    np_acts-logits-general · gemini-2.0-flash

    carrying out research or analysis

    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
     للمعارف
    -0.59
    unehmen
    -0.55
     możliwości
    -0.52
    RectangleBorder
    -0.50
    IsContent
    -0.49
     arrivant
    -0.49
     resultaat
    -0.49
     Umsetzung
    -0.49
     Freude
    -0.49
     CURIAM
    -0.48
    POSITIVE LOGITS
     rigorous
    0.71
    conducted
    0.70
     extensive
    0.66
     experiments
    0.66
    successful
    0.65
    analyses
    0.65
    experiments
    0.63
    studies
    0.63
     analyses
    0.62
     searches
    0.62
    Activations Density 0.545%

    No Known Activations