© 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. 18-GEMMASCOPE-RES-16K
    11. 13360
    Prev
    Next
    INDEX
    Explanations

    terms related to time intervals surrounding events, particularly before and after actions or treatments

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

    following "post" or "pre"

    np_acts-logits-general · gemini-2.0-flash

    pre and post health events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    неопр
    -0.57
     wireType
    -0.55
    ProgressHUD
    -0.53
     potuto
    -0.53
     QtWidgets
    -0.52
    примеча
    -0.52
     compleanno
    -0.52
    JvmStatic
    -0.51
    Jeografia
    -0.50
    manship
    -0.49
    POSITIVE LOGITS
     Covid
    0.80
     COVID
    0.76
     covid
    0.73
     coronavirus
    0.70
     pandemic
    0.69
     pandemi
    0.69
     crisis
    0.68
     Hurricane
    0.68
     corona
    0.67
    发表于
    0.67
    Activations Density 0.348%

    No Known Activations