© 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-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9648
    Prev
    Next
    INDEX
    Explanations

    references to coding or programming elements, particularly those involving object-oriented or functional programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.88
     typelib
    -0.71
     '\\;'
    -0.65
     ویکی‌پدی
    -0.62
     كومونز
    -0.60
    脚注の使い方
    -0.60
     ویکی‌آمباردا
    -0.58
    MessageOf
    -0.55
    ագրություններ
    -0.55
     OMITBAD
    -0.55
    POSITIVE LOGITS
     Chwiliwch
    0.56
     self
    0.48
     fac
    0.45
    InBackground
    0.43
     po
    0.43
     ready
    0.42
    dlg
    0.42
     klart
    0.41
     Chimney
    0.40
     mon
    0.40
    Activations Density 2.752%

    No Known Activations