© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14925
    Prev
    Next
    INDEX
    Explanations

    grammatical terms and structures related to language processing and syntax

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

    Grammatical terms: noun, verb, clause

    np_acts-logits-general · gemini-2.0-flash

    noun phrases and pronouns

    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
     ostavi
    -0.89
    ReusableCell
    -0.74
     الاطلاع
    -0.70
    createCanvas
    -0.69
    TestingModule
    -0.69
    PerformLayout
    -0.68
     ComVisible
    -0.67
     Roskov
    -0.66
     OFDb
    -0.63
    clusal
    -0.62
    POSITIVE LOGITS
     noun
    0.76
     preposition
    0.75
     verbs
    0.71
     modifier
    0.71
     nouns
    0.71
     adverb
    0.71
     adjective
    0.71
     verb
    0.69
    Noun
    0.67
     adverbs
    0.66
    Activations Density 0.316%

    No Known Activations