© 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. 22-GEMMASCOPE-RES-16K
    11. 12559
    Prev
    Next
    INDEX
    Explanations

    instances of the word "before" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text preceding "you", "she", "they", etc

    np_acts-logits-general · gemini-2.0-flash

    before followed by an event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.66
     vectorielles
    -0.63
    niosek
    -0.61
     følge
    -0.59
    BrowserModule
    -0.59
     kiệm
    -0.59
    ษัท
    -0.58
    くちゃ
    -0.56
     initComponents
    -0.56
    uarkan
    -0.55
    POSITIVE LOGITS
    hand
    1.11
     anyone
    0.93
     anything
    0.92
     any
    0.88
     they
    0.87
    HAND
    0.86
     embarking
    0.86
     proceeding
    0.83
    andafter
    0.82
     anybody
    0.78
    Activations Density 0.089%

    No Known Activations