© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3927
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations in a document

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

    Mathematical or physics equations/formulae

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and 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
    AnchorTagHelper
    -0.66
    الدراسه
    -0.63
     defaultstate
    -0.56
     createSprite
    -0.56
    webElementXpaths
    -0.56
    RectangleBorder
    -0.54
     mxArray
    -0.54
    Արտաքին
    -0.53
     initComponents
    -0.53
    tonode
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.75
    enumi
    0.69
     الحره
    0.69
     esternos
    0.67
     Muck
    0.66
    *}{
    0.65
    IMPORTED
    0.65
     méri
    0.65
    |}{
    0.63
    
    0.63
    Activations Density 0.343%

    No Known Activations