© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6158
    Prev
    Next
    INDEX
    Explanations

    tokens related to mathematical symbols and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '))
    
    -0.66
    "))
    
    -0.59
    '])
    
    -0.59
    canActivate
    -0.57
    VERTIS
    -0.56
    "])
    
    -0.56
     }}^{
    -0.55
    ">)</
    -0.54
    ')):
    -0.53
    Diweddarwch
    -0.53
    POSITIVE LOGITS
    IntoConstraints
    0.99
    ValueStyle
    0.89
    ConstraintMaker
    0.86
     nakalista
    0.84
     CreateTagHelper
    0.83
     NSCoder
    0.83
     purpoſe
    0.82
     propOrder
    0.80
     للمعارف
    0.78
     pleaſure
    0.77
    Activations Density 2.746%

    No Known Activations