© 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. 12833
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to formal expressions and constructs

    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
     McIntyre
    -0.78
     ")");
    -0.75
    mew
    -0.74
    miary
    -0.71
     newNode
    -0.68
     Paola
    -0.68
    polynomial
    -0.63
    CIE
    -0.63
    iyaki
    -0.62
     savages
    -0.62
    POSITIVE LOGITS
     فريبيس
    1.04
    {~
    0.84
    {{\
    0.82
    }{
    0.80
    ={[
    0.79
     jspb
    0.79
    DispatchToProps
    0.78
    Vidite
    0.78
     gynhyrchwyd
    0.78
     }^{[
    0.77
    Activations Density 1.606%

    No Known Activations