© 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. 11605
    Prev
    Next
    INDEX
    Explanations

    numeric references and possibly formatting elements from scientific or academic texts

    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
    LookAnd
    -0.63
    ptăm
    -0.43
     avoient
    -0.43
    tdessen
    -0.41
     pouvoit
    -0.41
     étoient
    -0.39
    RenderAtEndOf
    -0.38
    嘞
    -0.37
     sementara
    -0.37
     vielmehr
    -0.36
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.58
    TargetException
    0.50
    ImageContext
    0.50
     Expédié
    0.49
    tinyos
    0.47
     AssemblyProduct
    0.47
     సౌకర్య
    0.47
    endphp
    0.46
    asgi
    0.46
     farfetch
    0.46
    Activations Density 0.914%

    No Known Activations