© 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. 11163
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to magnetic materials and phenomena

    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
     ujednoznacz
    -0.82
    AutoScaleMode
    -0.81
     <>",
    -0.79
    jectures
    -0.72
    omie
    -0.71
     rowCount
    -0.68
    Espèce
    -0.67
     syscall
    -0.67
     eventName
    -0.67
    windowFixed
    -0.66
    POSITIVE LOGITS
     magnetic
    1.20
    magnetic
    1.08
     Magnetic
    1.07
    Magnetic
    1.07
     magnet
    1.05
    磁
    1.05
    magnet
    1.05
     MAGNET
    1.04
     magnets
    1.00
     magnétique
    0.96
    Activations Density 0.447%

    No Known Activations