© 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. 35-GEMMASCOPE-RES-16K
    11. 7531
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to genetic abnormalities and chromosomal analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.61
     dren
    -0.59
    InjectAttribute
    -0.58
    iſen
    -0.56
    存于互联网档案馆
    -0.54
     nonUne
    -0.54
    indoor
    -0.53
    StartTag
    -0.53
     Indoor
    -0.52
    AsUp
    -0.52
    POSITIVE LOGITS
     chromosome
    1.00
     chromosomes
    0.97
     chromosomal
    0.82
     Chromosome
    0.80
    chromosome
    0.76
    Chromosome
    0.75
    chrom
    0.73
     Chrom
    0.72
     хро
    0.69
    Chrom
    0.67
    Activations Density 1.409%

    No Known Activations