© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 10733
    Prev
    Next
    INDEX
    Explanations

    occurrences or variations of the word "before."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.95
    gdx
    -0.81
     følge
    -0.73
     Talley
    -0.69
     habet
    -0.69
     magasiner
    -0.68
    NUMERIC
    -0.67
     Messer
    -0.66
    gany
    -0.65
     jLabel
    -0.65
    POSITIVE LOGITS
    before
    1.91
    BEFORE
    1.89
     before
    1.89
     Before
    1.84
     BEFORE
    1.80
    Before
    1.76
     befo
    1.45
     sebelum
    1.40
     innan
    1.34
     før
    1.28
    Activations Density 0.055%

    No Known Activations