© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7512
    Prev
    Next
    INDEX
    Explanations

    references to medical treatments and their benefits

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

    Helps/enhances/stimulates something

    np_acts-logits-general · gemini-2.0-flash

    helps improve or relieve

    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
    脚注の使い方
    -0.53
    تقاوى
    -0.52
     الحره
    -0.48
    awtextra
    -0.46
    abstractmethod
    -0.44
    vfill
    -0.44
    ビー
    -0.44
    cticut
    -0.44
    OutOf
    -0.43
     doomed
    -0.42
    POSITIVE LOGITS
    Helps
    1.00
     helps
    0.99
     relieves
    0.99
     Helps
    0.99
     improves
    0.96
     help
    0.95
     relieve
    0.94
     relieving
    0.94
     improve
    0.94
    ช่วย
    0.92
    Activations Density 0.368%

    No Known Activations