© 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. 18-GEMMASCOPE-RES-16K
    11. 4373
    Prev
    Next
    INDEX
    Explanations

    elements related to health and medical terminology, particularly focusing on disorders and their descriptions

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

    appearing in titles or categories

    np_acts-logits-general · gemini-2.0-flash

    locations and categories

    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
    `,
    -1.25
     Мексичка
    -1.20
    .",
    -1.19
     consultato
    -1.08
    '],
    -1.02
    出版年
    -1.00
    '},
    -1.00
    NUMX
    -1.00
    \",
    -0.98
    存于互联网档案馆
    -0.98
    POSITIVE LOGITS
    ↵↵
    2.17
    <eos>
    1.72
    ↵
    1.67
    ↵↵↵
    1.65
    ↵↵↵↵
    1.31
    ↵↵↵↵↵
    1.20
    ↵↵↵↵↵↵↵
    0.97
    ↵↵↵↵↵↵
    0.95
    </h2>
    0.92
    ↵↵↵↵↵↵↵↵↵
    0.87
    Activations Density 4.167%

    No Known Activations