© 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. 422
    Prev
    Next
    INDEX
    Explanations

    structured data snippets, especially those related to configurations or settings

    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
     and
    -0.60
    ’
    -0.54
    のご
    -0.51
    ,
    -0.49
     đồng
    -0.49
     I
    -0.47
    ª
    -0.45
     l
    -0.45
    '
    -0.44
     Ein
    -0.43
    POSITIVE LOGITS
     myſelf
    0.91
     ſeveral
    0.91
     ſmall
    0.91
     quæ
    0.90
     تضيفلها
    0.90
    expandindo
    0.87
     reaſon
    0.87
     Theſe
    0.87
    IsContent
    0.86
     purpoſe
    0.85
    Activations Density 0.664%

    No Known Activations