© 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. 2817
    Prev
    Next
    INDEX
    Explanations

    references to scientific measurements and concepts in particle physics

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

    particle accelerators and colliders

    np_acts-logits-general · gemini-2.0-flash

    collider beam accelerator physics

    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
    Geplaatst
    -0.59
    Datuak
    -0.59
     Audiodateien
    -0.58
     ujednoznacz
    -0.58
    cshtml
    -0.54
     >=",
    -0.51
     AssemblyCulture
    -0.51
     disambiguazione
    -0.49
     Luftwaffe
    -0.48
    gut
    -0.48
    POSITIVE LOGITS
     accelerator
    0.95
     accelerators
    0.82
     beam
    0.73
     Accelerator
    0.72
    errHandler
    0.72
     aceler
    0.64
     collider
    0.63
    beam
    0.62
    acceler
    0.61
    Acceler
    0.61
    Activations Density 0.459%

    No Known Activations