© 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. 2-GEMMASCOPE-RES-16K
    11. 15617
    Prev
    Next
    INDEX
    Explanations

    patterns of whitespace and formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.64
     AssemblyCulture
    -0.51
     незавершена
    -0.51
     désolés
    -0.50
     виправивши
    -0.49
    الإنجليزية
    -0.48
    تقاوى
    -0.48
    indd
    -0.46
     my
    -0.46
     pubb
    -0.45
    POSITIVE LOGITS
     herbic
    0.64
    >>>>>>>
    0.61
    +#+
    0.60
    PRNewswire
    0.60
    loroethene
    0.59
    ContentValues
    0.58
    >>>>
    0.58
    rogels
    0.58
     Idy
    0.57
     utafitiHapana
    0.57
    Activations Density 1.089%

    No Known Activations