© 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. 22-GEMMASCOPE-RES-16K
    6. 3920
    Prev
    Next
    INDEX
    Explanations

    references to quantities or counts in various contexts

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

    Followed by quantity-related words

    np_acts-logits-general · gemini-2.0-flash

    a followed by quantify or singular nouns

    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
     őket
    -0.57
    harapkan
    -0.51
    eraard
    -0.50
     asimismo
    -0.47
     esclu
    -0.47
     jeweiligen
    -0.47
     belangrijkste
    -0.47
     appunto
    -0.46
     ovviamente
    -0.46
     pertanto
    -0.45
    POSITIVE LOGITS
     lot
    1.09
     few
    1.01
     ProtoMessage
    0.95
     estekak
    0.95
     LOT
    0.92
    WithIOException
    0.92
    few
    0.91
    lot
    0.91
    Билгалдахарш
    0.90
     sacco
    0.90
    Activations Density 0.327%

    No Known Activations