© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4156
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in a document

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

    Citations with initials

    np_acts-logits-general · gemini-2.0-flash

    initials and punctuation

    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
    Datuak
    -0.92
     تضيفلها
    -0.86
    InputBorder
    -0.83
     resourceCulture
    -0.79
     Савезне
    -0.78
    Portale
    -0.77
    AndEndTag
    -0.76
    parsedMessage
    -0.75
    исленность
    -0.73
     Anſ
    -0.71
    POSITIVE LOGITS
     J
    0.68
     M
    0.66
     A
    0.63
     G
    0.61
     C
    0.60
     T
    0.57
     S
    0.57
     D
    0.55
     E
    0.54
     B
    0.52
    Activations Density 0.155%

    No Known Activations