© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8772
    Prev
    Next
    INDEX
    Explanations

    instances of whitespace or line breaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ()))
    -0.60
     helst
    -0.54
    }")
    -0.54
     BorderRadius
    -0.53
    ");
    -0.52
     AdapterView
    -0.52
    "))
    -0.52
    ++)
    -0.51
     MainAxisSize
    -0.51
     hiburan
    -0.50
    POSITIVE LOGITS
    wpi
    0.71
    Бахар
    0.67
    riwal
    0.66
     calendriers
    0.64
    Santis
    0.60
    complexContent
    0.60
    dafx
    0.59
    RepeatedField
    0.58
     propOrder
    0.56
      
    0.56
    Activations Density 0.160%

    No Known Activations