© 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. 37-GEMMASCOPE-RES-16K
    11. 3581
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to DNA and viral replication processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viano
    -0.38
    Button
    -0.37
    FlatStyle
    -0.33
     незавершена
    -0.33
     basketball
    -0.33
     Gers
    -0.32
    Prote
    -0.32
    现
    -0.31
     AssemblyCulture
    -0.31
     Glau
    -0.31
    POSITIVE LOGITS
     DNA
    1.52
    DNA
    1.34
     dna
    1.09
    dna
    0.93
     nucleic
    0.90
     ADN
    0.88
    ADN
    0.88
     DN
    0.84
     Nucleic
    0.77
     deoxy
    0.74
    Activations Density 2.012%

    No Known Activations