© 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. 11-GEMMASCOPE-RES-16K
    11. 5253
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and symbols, particularly those involving big or bold formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.84
    RegressionTest
    -0.76
     PeEnEo
    -0.64
    EndProject
    -0.63
     препратки
    -0.61
    UserScript
    -0.60
     Мексичка
    -0.59
     ?>/
    -0.58
    })));
    -0.57
     Italijanski
    -0.56
    POSITIVE LOGITS
    mo
    1.46
    Mo
    1.06
     mo
    1.06
     Mo
    1.01
    MO
    0.87
     MO
    0.75
    мо
    0.68
    莫
    0.65
     мо
    0.64
    モ
    0.62
    Activations Density 0.250%

    No Known Activations