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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 1387
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific names and entities related to individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eliot
    -0.63
     Locator
    -0.57
    odorant
    -0.56
     Polak
    -0.55
     Josef
    -0.55
     Aguilar
    -0.54
     Keenan
    -0.54
     Anam
    -0.54
     Arad
    -0.54
     Mariam
    -0.53
    POSITIVE LOGITS
     BorderSide
    0.54
    transQ
    0.54
     Rhi
    0.51
     Blaine
    0.50
     Marlowe
    0.49
    tagHelperRunner
    0.48
    ########.
    0.48
    AppService
    0.48
    msgTypes
    0.48
     Mathilde
    0.47
    Activations Density 2.019%

    No Known Activations