© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 763
    Prev
    Next
    INDEX
    Explanations

    specific durations and time frames related to studies or clinical trials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netbeans
    -0.66
     NavController
    -0.65
    Spoljašnje
    -0.57
     lac
    -0.54
    oneofs
    -0.52
     nahilalakip
    -0.52
    [++
    -0.51
    ophilus
    -0.51
    OGND
    -0.51
    topped
    -0.50
    POSITIVE LOGITS
    bootstrapcdn
    0.74
     OFDb
    0.67
     WaitForSeconds
    0.65
    SpringRunner
    0.65
    quatch
    0.65
     présidentielle
    0.64
    mogat
    0.61
    +:+
    0.61
     pregnancy
    0.60
    Months
    0.59
    Activations Density 0.202%

    No Known Activations