© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10655
    Prev
    Next
    INDEX
    Explanations

    technical terms related to layers and components in scientific contexts

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

    Quantities, counts, or amounts

    np_acts-logits-general · gemini-2.0-flash

    names of countable things

    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
     utafitiHapana
    -0.57
     everywhere
    -0.56
    พาะ
    -0.53
    reportWebVitals
    -0.51
    这些
    -0.51
    everywhere
    -0.49
    cuentes
    -0.49
     թվական
    -0.48
     للمعارف
    -0.48
    mybatisplus
    -0.48
    POSITIVE LOGITS
     apiece
    1.05
    Kaynakça
    0.85
     plus
    0.81
     namely
    0.80
     подряд
    0.80
     Мексичка
    0.78
     ویکی‌پدیا
    0.77
     each
    0.73
    分别是
    0.72
     typelib
    0.70
    Activations Density 0.868%

    No Known Activations