© 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. 9-GEMMASCOPE-RES-16K
    11. 2838
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional phrases that indicate contrast or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     invariants
    -0.63
     pronti
    -0.61
     Forse
    -0.58
    dope
    -0.57
     fatica
    -0.56
     unknowns
    -0.56
     honte
    -0.56
     impunity
    -0.56
     Waldo
    -0.55
     Pind
    -0.55
    POSITIVE LOGITS
     also
    0.79
     برانيه
    0.68
    matchCondition
    0.64
    also
    0.56
    Jîn
    0.55
     también
    0.55
    ITHUB
    0.55
    argout
    0.52
    niająca
    0.51
    internalType
    0.50
    Activations Density 0.147%

    No Known Activations