© 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. 2-GEMMASCOPE-RES-16K
    11. 7626
    Prev
    Next
    INDEX
    Explanations

    instances of the word "relatively" used in various contexts

    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
    ja
    -0.55
    habad
    -0.54
    ud
    -0.53
     sắc
    -0.53
    (
    -0.52
    cha
    -0.52
    clar
    -0.52
    ay
    -0.51
    kan
    -0.51
    ik
    -0.50
    POSITIVE LOGITS
    relatively
    2.55
     relatively
    2.55
     Relatively
    2.38
     relativement
    1.99
     relativamente
    1.91
     comparatively
    1.88
     relativ
    1.64
     relative
    1.62
     fairly
    1.54
    比較的
    1.46
    Activations Density 0.073%

    No Known Activations