© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28453
    Prev
    Next
    INDEX
    Explanations

    the opening tokens or symbols in text that signify the beginning of a segment or block, typically indicating starts of sections or paragraphs

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

    list items separated by commas

    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
     gemeenten
    -0.49
    siez
    -0.48
    ग्री
    -0.48
    ensively
    -0.46
    Eloquent
    -0.46
     verticales
    -0.45
    ENDO
    -0.45
    âu
    -0.44
    źnie
    -0.44
     Escu
    -0.43
    POSITIVE LOGITS
     <=",
    0.83
    sizeCache
    0.72
    Jereo
    0.71
    tagHelperRunner
    0.71
    :✨
    0.71
    ,:),
    0.70
    省市镇
    0.70
    +#+#
    0.70
     AssemblyProduct
    0.68
    +#+
    0.65
    Activations Density 0.657%

    No Known Activations