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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13745
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physical phenomena and measurements

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

    "of" followed by quantity words

    np_acts-logits-general · gemini-2.0-flash

    orders of magnitude, quantities, ranges

    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
    +#+#
    -0.51
    Diwedd
    -0.46
    Sklici
    -0.45
    <bos>
    -0.45
    AndEndTag
    -0.44
     répar
    -0.43
     elif
    -0.43
     testSet
    -0.42
     nahilalakip
    -0.42
    ($__
    -0.41
    POSITIVE LOGITS
     tens
    1.08
     orders
    1.06
     order
    1.05
     hundreds
    0.94
     Order
    0.91
    order
    0.91
     Orders
    0.91
     ORDERS
    0.87
    Order
    0.86
     dizaines
    0.86
    Activations Density 1.233%

    No Known Activations