© 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. 24-GEMMASCOPE-RES-16K
    11. 6674
    Prev
    Next
    INDEX
    Explanations

    references to events or actions that occur before a certain point in time

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

    "before"

    np_acts-logits-general · gemini-2.0-flash

    before an event or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    évaluateur
    -0.68
    parsedMessage
    -0.68
    MessageTagHelper
    -0.62
     vectorielles
    -0.61
    uarkan
    -0.60
    BrowserModule
    -0.60
    ArrowToggle
    -0.60
    seamnă
    -0.57
     habet
    -0.56
    χι
    -0.56
    POSITIVE LOGITS
    hand
    1.21
    HAND
    1.00
     they
    0.98
     anyone
    0.95
     embarking
    0.92
     anything
    0.90
     any
    0.85
     proceeding
    0.83
     anybody
    0.82
     heading
    0.81
    Activations Density 0.114%

    No Known Activations