© 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. 4539
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or sequential processes

    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
     themſelves
    -1.02
     himſelf
    -0.99
     pleaſure
    -0.93
     myſelf
    -0.90
     Theſe
    -0.88
     BorderRadius
    -0.85
     poffe
    -0.84
     Jefus
    -0.84
     Monfieur
    -0.81
     leſs
    -0.80
    POSITIVE LOGITS
     inorder
    1.37
     afin
    1.21
     order
    1.12
    inorder
    1.08
    Afin
    1.04
    为了
    1.01
     чтобы
    0.95
     כדי
    0.92
    為了
    0.91
     Afin
    0.91
    Activations Density 0.162%

    No Known Activations