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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3053
    Prev
    Next
    INDEX
    Explanations

    mixed-language tokens, specifically those that may include Arabic characters or Latin script letters

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

    The letter "D" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    D. followed by words or abbreviations

    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
    rativa
    -0.56
     surla
    -0.56
     Audiodateien
    -0.53
    AndroidJUnit
    -0.51
     noten
    -0.46
    deh
    -0.46
    ArgumentParser
    -0.46
     mí
    -0.46
     initComponents
    -0.46
     Signalez
    -0.46
    POSITIVE LOGITS
     traffico
    0.60
    :✨
    0.59
     concorso
    0.55
     Wettbewerb
    0.54
    stateProvider
    0.53
    OutputType
    0.53
     mattino
    0.53
     prossimo
    0.52
     tratto
    0.52
    ValueGenerated
    0.51
    Activations Density 0.100%

    No Known Activations