© 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. 5968
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their contributions in various contexts

    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
     isolato
    -0.48
    Pratique
    -0.48
     thereon
    -0.47
     Flasche
    -0.47
     asegurado
    -0.47
     poichè
    -0.46
    mogat
    -0.46
     acompañado
    -0.45
     prohibido
    -0.45
     definately
    -0.44
    POSITIVE LOGITS
     Their
    0.75
     These
    0.63
     Those
    0.62
     Its
    0.61
     Them
    0.60
     They
    0.60
    IUrlHelper
    0.60
    EDEFAULT
    0.56
     That
    0.55
     Your
    0.55
    Activations Density 0.429%

    No Known Activations