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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3244
    Prev
    Next
    INDEX
    Explanations

    names and terms related to cultural or traditional aspects

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

    with diacritics (especially ā/ş/ş)

    np_acts-logits-general · gemini-2.0-flash

    Persian and Turkic place names

    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
    ourced
    -0.43
    urk
    -0.42
    gorov
    -0.42
     av
    -0.39
    utzung
    -0.39
     ve
    -0.39
    vaadin
    -0.39
     ст
    -0.39
    اطر
    -0.39
    astas
    -0.38
    POSITIVE LOGITS
    出版年
    0.96
     OFDb
    0.73
     BorderRadius
    0.71
     purpoſe
    0.66
     $_"
    0.66
     Theſe
    0.65
     faſt
    0.64
     AppComponent
    0.64
     تضيفلها
    0.64
    AttributeSet
    0.63
    Activations Density 0.108%

    No Known Activations