© 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. 22-GEMMASCOPE-RES-16K
    11. 9818
    Prev
    Next
    INDEX
    Explanations

    references to the word "down" and its variations

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

    "down" followed by various prepositions

    np_acts-logits-general · gemini-2.0-flash

    payment and regulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.77
     AssemblyCompany
    -0.76
    adecimal
    -0.71
    IVEREF
    -0.71
     ComVisible
    -0.71
    IBOutlet
    -0.70
    ształ
    -0.69
    djangoproject
    -0.68
    Viki
    -0.68
     nahilalakip
    -0.67
    POSITIVE LOGITS
    pour
    0.85
    sizing
    0.80
    hill
    0.67
    payment
    0.67
    sized
    0.66
    stream
    0.62
     Down
    0.61
    Downs
    0.61
    size
    0.61
    river
    0.60
    Activations Density 0.081%

    No Known Activations