© 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. 10901
    Prev
    Next
    INDEX
    Explanations

    negations and limitations

    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
     EconPapers
    -0.57
    parsedMessage
    -0.56
    Хьажоргаш
    -0.56
     Biôgrafia
    -0.54
     propOrder
    -0.51
     հղումներ
    -0.50
    Aiheesta
    -0.49
     يتيمه
    -0.49
     שוליים
    -0.49
     мәкал
    -0.49
    POSITIVE LOGITS
    theless
    0.56
    Anyhow
    0.50
     obstante
    0.47
    lijk
    0.43
    lillah
    0.42
    жели
    0.42
    beit
    0.41
    wise
    0.41
    etheless
    0.41
    licet
    0.41
    Activations Density 0.448%

    No Known Activations