© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9174
    Prev
    Next
    INDEX
    Explanations

    references to specific brands or products

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

    Followed by "pc", "online", or "australia"

    np_acts-logits-general · gemini-2.0-flash

    shoes, buy, online, analysis, australia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.33
     administracy
    -0.30
    bootstrapcdn
    -0.30
     adicionales
    -0.29
     mundos
    -0.28
     najdete
    -0.28
     comédie
    -0.26
    够了
    -0.26
     asesor
    -0.26
     vulnerables
    -0.26
    POSITIVE LOGITS
     informée
    0.89
     @"/
    0.89
    SourceChecksum
    0.82
    rrggbb
    0.77
    ंदीखरीदारी
    0.75
    WithIOException
    0.74
     protoimpl
    0.73
     ProtoMessage
    0.72
    <unused79>
    0.72
    <unused28>
    0.72
    Activations Density 0.343%

    No Known Activations