© 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. 8-GEMMASCOPE-RES-16K
    11. 5159
    Prev
    Next
    INDEX
    Explanations

    the beginning and ending tags of sections or paragraphs in structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -1.12
     themſelves
    -1.09
     himſelf
    -1.08
     myſelf
    -1.07
     houſe
    -1.04
     itſelf
    -1.01
     ſeveral
    -1.00
     Anſ
    -1.00
     iſt
    -0.99
     reaſon
    -0.99
    POSITIVE LOGITS
     And
    1.04
     và
    1.04
     και
    1.03
     и
    0.97
     and
    0.96
    そして
    0.92
     \&
    0.91
     و
    0.87
     AND
    0.86
     och
    0.82
    Activations Density 0.029%

    No Known Activations