© 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. 34-GEMMASCOPE-RES-16K
    11. 10846
    Prev
    Next
    INDEX
    Explanations

    references to books and their publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     literature
    -0.42
     privados
    -0.36
    Literature
    -0.36
    oh
    -0.35
    ansu
    -0.35
    文獻
    -0.34
     paio
    -0.34
     garagem
    -0.33
     LITERATURE
    -0.33
     privadas
    -0.33
    POSITIVE LOGITS
     paperback
    0.82
     hardcover
    0.80
     Hardcover
    0.73
     Paperback
    0.71
     ISBN
    0.67
     soft
    0.66
    Hardcover
    0.65
     Kindle
    0.63
    Paperback
    0.60
    soft
    0.58
    Activations Density 0.314%

    No Known Activations