© 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. 10067
    Prev
    Next
    INDEX
    Explanations

    mathematical solutions and expressions related to equations and their properties

    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
     Kap
    -0.32
    abol
    -0.31
    deuse
    -0.31
    upsi
    -0.31
     Dawn
    -0.31
    pev
    -0.30
     Cio
    -0.30
     Acc
    -0.30
    Acc
    -0.30
     useContext
    -0.30
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
     solution
    0.73
     soluzione
    0.68
     nghiệm
    0.66
     solutions
    0.60
     SOLUTION
    0.60
    solution
    0.59
    Solving
    0.59
    Hauptartikel
    0.58
     Lösung
    0.58
    Activations Density 1.697%

    No Known Activations