© 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. 6998
    Prev
    Next
    INDEX
    Explanations

    terms related to statistics and growth rates in various contexts

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

    Increase after a noun

    np_acts-logits-general · gemini-2.0-flash

    increase or rise

    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
    onViewCreated
    -0.60
    ########.
    -0.55
     (−
    -0.54
    errHandler
    -0.54
     headless
    -0.51
    headless
    -0.50
    Unload
    -0.49
    =−
    -0.49
     freshest
    -0.49
    zeň
    -0.49
    POSITIVE LOGITS
     increase
    2.31
     increased
    2.19
     increases
    2.15
    increase
    2.06
     Increase
    2.04
    Increase
    2.01
    increased
    1.95
     increasing
    1.94
     Increased
    1.89
     INCREASE
    1.88
    Activations Density 1.016%

    No Known Activations