Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3075
    Prev
    Next
    INDEX
    Explanations

    attributes related to layout specifications in code

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

    `wrap_content` in Android XML layouts

    np_acts-logits-general · gemini-2.0-flash

    android layout attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.68
     Echin
    -0.49
     occidentalis
    -0.49
     Benitez
    -0.48
    mybatisplus
    -0.47
     chêne
    -0.47
    Docket
    -0.46
     montr
    -0.46
    Bind
    -0.46
     Utile
    -0.46
    POSITIVE LOGITS
    ImageContext
    0.72
     ExecuteAsync
    0.72
    CloseOperation
    0.70
    ArgumentParser
    0.65
    ValueStyle
    0.62
    ]<<"
    0.61
     للمعارف
    0.60
     ]
    
    0.59
    }{*}{}
    0.58
    .*")]
    0.58
    Activations Density 0.050%

    No Known Activations