© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5691
    Prev
    Next
    INDEX
    Explanations

    phrases that mention workarounds or fixes for technical problems

    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
    UnsafeEnabled
    -0.93
    URLException
    -0.90
     itſelf
    -0.90
    NameInMap
    -0.89
     oprot
    -0.87
    :✨
    -0.86
     SEDS
    -0.83
     Мексичка
    -0.81
     houſe
    -0.81
     myſelf
    -0.80
    POSITIVE LOGITS
    [*]
    0.49
    Bibliographie
    0.49
     ElementRef
    0.48
     해
    0.47
    鑑
    0.45
    licherweise
    0.44
    .*
    0.44
    []
    0.43
    serviceWorker
    0.43
     diper
    0.42
    Activations Density 1.043%

    No Known Activations