© 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. 20-GEMMASCOPE-RES-16K
    11. 5504
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical notation and terminology

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

    Text within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    roman math identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.68
    addCriterion
    -0.66
     noDo
    -0.64
    клопе
    -0.63
    BagConstraints
    -0.60
     Roskov
    -0.59
     <<<<<<<<<<<<<<
    -0.57
     @"/
    -0.57
    nore
    -0.56
    षण
    -0.56
    POSITIVE LOGITS
     mukana
    0.64
     tweezers
    0.57
    apatalk
    0.56
    whale
    0.53
    ".
    0.53
    存于互联网档案馆
    0.53
     VCR
    0.51
     pamph
    0.51
     tibial
    0.51
     bookseller
    0.50
    Activations Density 0.087%

    No Known Activations