© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 11556
    Prev
    Next
    INDEX
    Explanations

    references to characters and elements from a specific fictional universe or lore

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     angef
    -0.29
     dienst
    -0.29
     Undang
    -0.29
    Tikang
    -0.29
    iempos
    -0.28
     &___
    -0.28
     vogliamo
    -0.28
    jelent
    -0.27
    AssignableFrom
    -0.27
     hjär
    -0.27
    POSITIVE LOGITS
     propOrder
    0.73
    MigrationBuilder
    0.70
    exitRule
    0.66
    Personendaten
    0.66
     Pend
    0.66
     tribut
    0.63
    Pend
    0.62
    Duel
    0.61
     estekak
    0.61
     kasarigan
    0.61
    Activations Density 0.480%

    No Known Activations