© 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 EvalsExportsAPI 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. 2911
    Prev
    Next
    INDEX
    Explanations

    elements related to experimental design and methodology

    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
    KommentareTeilen
    -0.72
    ########.
    -0.68
     estimés
    -0.66
    schedulers
    -0.64
    IntoConstraints
    -0.61
    Бахар
    -0.60
    PerformLayout
    -0.59
    BeginInit
    -0.57
     trouvera
    -0.57
    tinyos
    -0.57
    POSITIVE LOGITS
     test
    1.41
     tests
    1.26
     testing
    1.25
     experiments
    1.11
     experiment
    1.10
     Test
    1.07
    Test
    1.05
     Testing
    1.03
     experimental
    1.02
     TEST
    1.00
    Activations Density 1.233%

    No Known Activations