© 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. 5-GEMMASCOPE-RES-16K
    11. 15945
    Prev
    Next
    INDEX
    Explanations

    instances that signify irony or unexpected outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.57
    ArgsConstructor
    -0.57
     OGS
    -0.57
    thâu
    -0.56
    PerformLayout
    -0.56
    новниш
    -0.54
     Marius
    -0.53
     Himo
    -0.52
     parms
    -0.52
     intensities
    -0.51
    POSITIVE LOGITS
     Ironically
    0.68
     ironically
    0.65
    brigens
    0.63
    xically
    0.59
     fact
    0.59
    Interestingly
    0.58
     faktisk
    0.57
    何と
    0.57
    なんと
    0.56
    Кстати
    0.56
    Activations Density 0.247%

    No Known Activations