© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4187
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to scientific experiments and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setz
    -0.47
    Autoritní
    -0.46
    ummer
    -0.44
    CCESS
    -0.44
    ¦
    -0.43
     work
    -0.43
    neté
    -0.43
    arschijnlijk
    -0.42
    szy
    -0.42
    Normdaten
    -0.41
    POSITIVE LOGITS
     benchmark
    0.78
     untreated
    0.75
     placebo
    0.71
     baseline
    0.71
    benchmark
    0.71
     ""],
    0.70
    SpringBootTest
    0.70
     comparator
    0.68
     benchmarks
    0.68
     Benchmark
    0.67
    Activations Density 2.419%

    No Known Activations