© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30311
    Prev
    Next
    INDEX
    Explanations

    occurrences of the special token indicating the beginning of a new segment or block of text

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

    numbers, symbols, and foreign words

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    τή
    -0.54
    हो
    -0.47
     etc
    -0.47
    Hymen
    -0.47
    LabelTagHelper
    -0.46
     senare
    -0.44
     -
    -0.43
    ابراین
    -0.43
     Summary
    -0.42
    Arial
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.91
     насељу
    0.87
     externi
    0.85
     IBOutlet
    0.84
    Datuak
    0.83
    存于互联网档案馆
    0.79
     disambiguazione
    0.76
     pinulongan
    0.76
    Vidite
    0.75
     Chwiliwch
    0.75
    Activations Density 0.288%

    No Known Activations