© 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. 16-GEMMASCOPE-RES-16K
    11. 12716
    Prev
    Next
    INDEX
    Explanations

    negations and exceptions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.52
    AndEndTag
    -0.48
     pleaſure
    -0.47
    EndInit
    -0.46
    enderror
    -0.46
    TagHelper
    -0.44
    ctest
    -0.44
    #+#
    -0.42
     LoginPage
    -0.41
    出版年
    -0.41
    POSITIVE LOGITS
     ujednoznacz
    0.64
     ilman
    0.60
     non
    0.56
     Non
    0.56
    脚注の使い方
    0.53
     zonder
    0.51
    Non
    0.50
     uden
    0.50
    Ohne
    0.50
     عدم
    0.49
    Activations Density 0.621%

    No Known Activations