© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4571
    Prev
    Next
    INDEX
    Explanations

    transitions or sequences marked by the word "Then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.71
     himſelf
    -0.68
     Irm
    -0.66
    noinspection
    -0.62
     purpoſe
    -0.62
    Unmanaged
    -0.61
    __/
    -0.61
     Harlow
    -0.60
    neſs
    -0.60
    Kaieteur
    -0.60
    POSITIVE LOGITS
     then
    3.17
     Then
    3.12
    Then
    3.07
    then
    2.87
     THEN
    2.76
    THEN
    2.62
     entonces
    2.16
     então
    1.95
     dann
    1.90
    Entonces
    1.86
    Activations Density 0.115%

    No Known Activations