© 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. 5386
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their impacts on identity and memory

    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
     estekak
    -0.43
     japonesa
    -0.41
     Japão
    -0.40
     mangá
    -0.40
     japonaise
    -0.39
    ImageContext
    -0.38
     япон
    -0.38
     Jepang
    -0.38
    Tikang
    -0.37
     ژاپ
    -0.37
    POSITIVE LOGITS
     Serbian
    1.84
     Serbia
    1.71
     Serb
    1.59
     Serbs
    1.55
     Belgrade
    1.55
     Balkan
    1.52
    Serbia
    1.49
     Kosovo
    1.46
     Bosnia
    1.45
     Balkans
    1.45
    Activations Density 0.270%

    No Known Activations