© 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. 16-GEMMASCOPE-RES-16K
    11. 2170
    Prev
    Next
    INDEX
    Explanations

    punctuation symbols appearing in the text

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

    Code using `println` (print statements)

    np_acts-logits-general · gemini-2.0-flash

    println

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -1.15
     fubject
    -0.93
    RegistryLite
    -0.91
    SourceChecksum
    -0.88
    Personendaten
    -0.86
     fevere
    -0.85
    GEBURTSDATUM
    -0.84
     Efq
    -0.84
     Monfieur
    -0.83
     onderhoud
    -0.82
    POSITIVE LOGITS
    println
    0.77
     Wur
    0.44
     println
    0.44
    ByUrl
    0.44
      
    0.42
    哇
    0.41
     Col
    0.41
    倒
    0.41
    推
    0.39
    logies
    0.39
    Activations Density 0.007%

    No Known Activations