© 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. 12-GEMMASCOPE-RES-16K
    11. 11676
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases and their relationships

    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
     douce
    -0.57
     برانيه
    -0.55
     the
    -0.55
    kelijke
    -0.54
     arasında
    -0.53
     chacun
    -0.53
    igheid
    -0.52
    argento
    -0.51
     abstrait
    -0.51
     néglig
    -0.51
    POSITIVE LOGITS
    DeleteBehavior
    0.74
    findpost
    0.74
     CreateTagHelper
    0.69
    ...@
    0.69
    RegressionTest
    0.68
    ……"
    0.64
    GEBURTSDATUM
    0.61
    Personensuche
    0.61
     تضيفلها
    0.60
    ListFragment
    0.60
    Activations Density 0.772%

    No Known Activations