© 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. 5213
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to medical or scientific contexts, particularly in fields like statistics and healthcare

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

    that express uncertainty or possibility

    np_acts-logits-general · gemini-2.0-flash

    even, possibly adding emphasis

    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
     незавершена
    -0.71
     oprot
    -0.64
    AutoScaleMode
    -0.61
     viewType
    -0.58
     neceff
    -0.57
    OGND
    -0.54
    而已
    -0.52
    DrawerToggle
    -0.52
     ſtate
    -0.52
    reactstrap
    -0.52
    POSITIVE LOGITS
     even
    4.97
    even
    4.32
    Even
    3.74
     Even
    3.66
     EVEN
    3.52
     даже
    3.40
     sogar
    3.38
     persino
    3.24
     навіть
    3.23
     incluso
    3.22
    Activations Density 0.847%

    No Known Activations