© 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. 21-GEMMASCOPE-RES-16K
    6. 12134
    Prev
    Next
    INDEX
    Explanations

    specific technical terms or acronyms related to data management and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ธ์
    -0.66
     numberWith
    -0.63
    arXiv
    -0.58
    ExtendWith
    -0.56
    Hauptartikel
    -0.56
    日閲覧
    -0.54
     gratify
    -0.53
    rungsseite
    -0.52
    setVerticalGroup
    -0.52
     serializers
    -0.52
    POSITIVE LOGITS
     lick
    0.60
     Vik
    0.57
     fermés
    0.55
     normaux
    0.53
     yc
    0.52
    irc
    0.52
     AMP
    0.50
     stessi
    0.50
    válasz
    0.50
     licking
    0.49
    Activations Density 0.505%

    No Known Activations