© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 9608
    Prev
    Next
    INDEX
    Explanations

    names and terms related to characters and events in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     måde
    -0.48
     dø
    -0.47
     economica
    -0.47
     onderhoud
    -0.45
     toekomst
    -0.44
     gouden
    -0.41
     werking
    -0.41
     politie
    -0.41
     plads
    -0.41
     elfog
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.73
     nonUne
    0.72
    ScopeManager
    0.63
     JpaRepository
    0.61
    Portail
    0.61
     GenerationType
    0.59
     EconPapers
    0.59
     protoimpl
    0.58
     חיצוניים
    0.57
     '\\;'
    0.57
    Activations Density 1.380%

    No Known Activations