© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14934
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology and notations related to various fields of mathematics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Begins with "mathcal"

    np_acts-logits-general · gemini-2.0-flash

    $\mathcal{}$ followed by symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -1.06
     disambiguazione
    -0.71
    onViewCreated
    -0.68
    NameInMap
    -0.64
     otomatig
    -0.64
    featureID
    -0.63
     đốc
    -0.63
    antMatchers
    -0.63
    ViewFeatures
    -0.62
     AssemblyVersion
    -0.61
    POSITIVE LOGITS
    mathcal
    1.07
    igraphic
    0.60
    ,$_
    0.58
     Merri
    0.58
     clic
    0.56
     Aguas
    0.56
    acchar
    0.55
    mathscr
    0.55
     Kell
    0.54
     Lizzie
    0.51
    Activations Density 0.257%

    No Known Activations