© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2918
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and syntax in programming languages

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

    Code, imports, and special characters

    np_acts-logits-general · gemini-2.0-flash

    instructions, care, overly generous

    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
    RegressionTest
    -0.96
    出版年
    -0.85
    تقاوى
    -0.78
     kasarigan
    -0.78
    Tembelea
    -0.75
    دانشنامهٔ
    -0.74
    脚注の使い方
    -0.74
     Wikiseite
    -0.74
    StructEnd
    -0.71
    })*/
    -0.70
    POSITIVE LOGITS
    ↵↵
    0.54
    ↵
    0.48
    JdbcTemplate
    0.46
     useParams
    0.45
    multer
    0.45
     AutoMapper
    0.43
      
    0.41
     useDispatch
    0.41
    X
    0.40
     FormBuilder
    0.39
    Activations Density 0.051%

    No Known Activations