© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    details about athletic achievements and statistics

    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
     للمعارف
    -0.53
    SharedDtor
    -0.53
     дописавши
    -0.51
     aquifer
    -0.50
    OGND
    -0.50
    enumi
    -0.48
    Numerology
    -0.48
     Spisak
    -0.47
     تضيفلها
    -0.47
     &___
    -0.47
    POSITIVE LOGITS
    
    0.72
     Class
    0.68
    indd
    0.58
    DockStyle
    0.57
    GOTREF
    0.56
     national
    0.54
     state
    0.53
     Lengkap
    0.52
     AA
    0.52
    __":
    0.51
    Activations Density 0.135%

    No Known Activations