© 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. 37-GEMMASCOPE-RES-16K
    11. 3814
    Prev
    Next
    INDEX
    Explanations

    variations of the word "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zuführen
    -0.39
    ///</
    -0.38
     least
    -0.38
    itées
    -0.38
    obenz
    -0.38
    OGND
    -0.36
    HeaderText
    -0.35
    xture
    -0.35
    CppMethod
    -0.35
    ewski
    -0.34
    POSITIVE LOGITS
    Demand
    0.70
     Demand
    0.69
     demand
    0.64
    demand
    0.63
     DEMAND
    0.60
    SharedDtor
    0.51
     poffible
    0.50
     boarding
    0.49
     Administrativna
    0.49
    Boarding
    0.49
    Activations Density 0.191%

    No Known Activations