© 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. 40-GEMMASCOPE-RES-16K
    11. 5258
    Prev
    Next
    INDEX
    Explanations

    numerical values or sequences within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.52
    lapsingToolbar
    -0.50
    ßig
    -0.49
     дописавши
    -0.47
    HasAnnotation
    -0.45
    th
    -0.45
    ſelf
    -0.44
     autorytatywna
    -0.44
    CopyWith
    -0.44
    InjectAttribute
    -0.43
    POSITIVE LOGITS
    nd
    1.40
    nds
    0.82
    ND
    0.79
     nd
    0.75
    ndy
    0.68
    ndry
    0.59
    ndia
    0.58
    Nd
    0.57
    ndr
    0.57
    ndt
    0.54
    Activations Density 1.742%

    No Known Activations