© 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. 12-GEMMASCOPE-RES-16K
    6. 3437
    Prev
    Next
    INDEX
    Explanations

    references to ownership and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.79
    DJANGO
    -0.55
     betweenstory
    -0.55
    HIRE
    -0.51
     تانيه
    -0.47
     typelib
    -0.47
    versiti
    -0.46
     iArr
    -0.46
     EconPapers
    -0.45
     hac
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    0.64
     irány
    0.57
     unilaterally
    0.57
     vezet
    0.56
    responsible
    0.56
     autorité
    0.56
    closedir
    0.55
     leiding
    0.55
     geomé
    0.55
     tramonto
    0.54
    Activations Density 0.536%

    No Known Activations