© 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. 11665
    Prev
    Next
    INDEX
    Explanations

    references to familial connections and personal lineage

    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
     rather
    -0.68
     både
    -0.66
     both
    -0.66
     almost
    -0.63
    而不是
    -0.59
     plutôt
    -0.59
     istället
    -0.57
    rather
    -0.57
    almost
    -0.56
     somewhat
    -0.56
    POSITIVE LOGITS
     anymore
    2.02
     nor
    1.98
     anything
    1.72
    anything
    1.42
     any
    1.38
    有任何
    1.38
     anywhere
    1.35
    nor
    1.35
     siquiera
    1.31
     anybody
    1.29
    Activations Density 3.084%

    No Known Activations