© 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. 3751
    Prev
    Next
    INDEX
    Explanations

    technical terms and relationships related to physics and mathematics

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

    "Approximately", "about," or similar quantifiers

    np_acts-logits-general · gemini-2.0-flash

    approximately

    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
    )++;
    -0.54
    WebControls
    -0.47
    dingen
    -0.46
    竟然是
    -0.46
    ynb
    -0.45
    itattu
    -0.44
    曖昧さ回避
    -0.44
     ولو
    -0.44
    AdapterFactory
    -0.44
    νη
    -0.43
    POSITIVE LOGITS
     approximately
    2.39
     about
    2.17
    approximately
    2.07
    about
    1.99
     Approximately
    1.96
     approx
    1.94
    Approximately
    1.91
     roughly
    1.85
     aproximadamente
    1.80
    About
    1.77
    Activations Density 0.768%

    No Known Activations