© 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. 35-GEMMASCOPE-RES-16K
    11. 7444
    Prev
    Next
    INDEX
    Explanations

    information related to motorsport events and championships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kkue
    -0.47
    Fordítás
    -0.39
    zkę
    -0.38
     Lingkungan
    -0.37
     alliance
    -0.37
    holdet
    -0.37
     alliances
    -0.36
     Wheelchair
    -0.36
    placa
    -0.35
    Alliance
    -0.35
    POSITIVE LOGITS
     track
    0.89
     tracks
    0.85
     circuit
    0.82
     circuits
    0.78
    circuit
    0.72
     circuito
    0.72
    track
    0.69
     Circuit
    0.69
     المعيارى
    0.68
    Circuit
    0.68
    Activations Density 0.263%

    No Known Activations