© 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. 17-GEMMASCOPE-RES-16K
    11. 7622
    Prev
    Next
    INDEX
    Explanations

    special tokens used for marking the beginning or delineating sections in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.82
    webElementGuid
    -0.81
    发表于
    -0.76
    MessageTagHelper
    -0.73
    AndroidJUnit
    -0.70
    Gweler
    -0.68
    RenderAtEndOf
    -0.67
    gameserver
    -0.66
     defaultstate
    -0.66
     دیکھیے
    -0.64
    POSITIVE LOGITS
    Linq
    2.48
    Collectors
    0.63
     LIN
    0.61
     Lin
    0.58
     Ufer
    0.52
    Queryable
    0.51
    ynos
    0.51
    Linn
    0.50
    LIN
    0.49
     minOccurs
    0.49
    Activations Density 0.009%

    No Known Activations