© 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. 18-GEMMASCOPE-RES-16K
    11. 9027
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols, particularly dashes and hyphens

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

    Page number citations

    np_acts-logits-general · gemini-2.0-flash

    page numbers and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -1.15
    CodedInputStream
    -0.80
    +#+#
    -0.74
     '\\;'
    -0.69
     AssemblyCulture
    -0.69
     незавершена
    -0.69
    HideFlags
    -0.68
    parsedMessage
    -0.65
    تقاوى
    -0.64
    GEBURTSDATUM
    -0.63
    POSITIVE LOGITS
    Véxase
    0.59
     finnas
    0.51
     användas
    0.51
     tė
    0.51
     tourne
    0.50
    inverno
    0.50
    Rohy
    0.50
     věci
    0.50
     définiti
    0.49
     cérami
    0.48
    Activations Density 0.176%

    No Known Activations