© 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. 10006
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sand" or variations thereof

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

    preceding "il", "ton", or "str"

    np_acts-logits-general · gemini-2.0-flash

    sand, sandwiched, sandilands, sand springs, sandton

    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
    er
    -0.77
    แน
    -0.54
     Apparent
    -0.54
    Eloquent
    -0.51
    zają
    -0.48
    erli
    -0.48
     contacts
    -0.47
     Salamanca
    -0.47
    jfree
    -0.46
     apparent
    -0.46
    POSITIVE LOGITS
    MLLoader
    0.73
    AndroidJUnit
    0.71
     AssemblyCompany
    0.71
    complexContent
    0.70
    wic
    0.69
    wiches
    0.63
     Paglinawan
    0.62
    ReusableCell
    0.61
    WICH
    0.60
    Pyx
    0.60
    Activations Density 0.134%

    No Known Activations