© 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. 16-GEMMASCOPE-RES-16K
    11. 8376
    Prev
    Next
    INDEX
    Explanations

    SQL-like syntax and data manipulation commands

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

    starting with "To" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    "to" and "from"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TAINMENT
    -0.57
    
    -0.56
    calaureate
    -0.54
     Scherer
    -0.52
    onuclear
    -0.49
    NÍ
    -0.49
    ული
    -0.48
    eski
    -0.47
    Préparation
    -0.47
    anthrene
    -0.46
    POSITIVE LOGITS
    AddTagHelper
    0.88
    TO
    0.82
    To
    0.78
     TO
    0.78
     utafitiHapana
    0.74
     Toh
    0.74
     To
    0.72
     Toad
    0.71
     Tole
    0.71
     Toe
    0.69
    Activations Density 0.274%

    No Known Activations