© 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. 20-GEMMASCOPE-RES-16K
    6. 15089
    Prev
    Next
    INDEX
    Explanations

    distinct Hungarian names and other identifiers

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

    Hungarian language or characters

    np_acts-logits-general · gemini-2.0-flash

    Hungarian and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.16
     itſelf
    -1.11
     Monfieur
    -1.01
     Phry
    -0.97
     Athenians
    -0.97
     preſent
    -0.97
     ſever
    -0.96
     Cæsar
    -0.95
     monasteries
    -0.94
     Euphrates
    -0.94
    POSITIVE LOGITS
     egy
    0.84
     és
    0.79
     az
    0.75
     Sz
    0.74
     sz
    0.71
     nem
    0.68
     ny
    0.67
     é
    0.65
     rend
    0.64
     meg
    0.64
    Activations Density 0.032%

    No Known Activations