© 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. 38-GEMMASCOPE-RES-16K
    11. 7891
    Prev
    Next
    INDEX
    Explanations

    references to new ideas, products, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actualmente
    -0.50
    Datuak
    -0.48
     currently
    -0.45
     Unterschiede
    -0.44
     derzeit
    -0.44
     mesmas
    -0.43
     następnie
    -0.43
    现有
    -0.43
     Unterschied
    -0.43
     gegenwär
    -0.43
    POSITIVE LOGITS
     arrivals
    0.90
     entrants
    0.87
     additions
    0.86
     entrant
    0.84
    sworth
    0.84
     generation
    0.83
    fang
    0.79
    swire
    0.74
     recruits
    0.74
     addition
    0.73
    Activations Density 0.247%

    No Known Activations