© 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. 15869
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols commonly used in mathematical notation

    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
    SequentialGroup
    -0.61
    先是
    -0.56
     فريبيس
    -0.56
     layui
    -0.54
     Le
    -0.54
     ri
    -0.52
    emen
    -0.52
    nya
    -0.51
    ỳ
    -0.49
    uens
    -0.48
    POSITIVE LOGITS
     ſtate
    1.01
     pleaſure
    0.98
     purpoſe
    0.97
    Tikang
    0.95
     Jefus
    0.93
     $\$
    0.92
    Hochspringen
    0.90
     theſe
    0.88
     uſe
    0.87
     ſhould
    0.86
    Activations Density 1.088%

    No Known Activations