© 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. 0-GEMMASCOPE-RES-16K
    11. 14864
    Prev
    Next
    INDEX
    Explanations

    references to mirrors and their various properties or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.89
     desmotivaciones
    -0.88
     defaultstate
    -0.83
    RegressionTest
    -0.79
     indígen
    -0.76
    verifyException
    -0.73
     miniaturka
    -0.71
     noastre
    -0.70
     increí
    -0.70
     nôtre
    -0.69
    POSITIVE LOGITS
     mirror
    1.02
     Mirror
    0.84
     mirrors
    0.79
    mir
    0.69
    mirror
    0.69
     mir
    0.67
     Mira
    0.65
     Mir
    0.64
    ze
    0.63
     wings
    0.63
    Activations Density 0.184%

    No Known Activations