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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 472
    Prev
    Next
    INDEX
    Explanations

    JSON or code-related syntax elements, particularly involving strings and keys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.57
    ']))
    -0.54
    "]))
    -0.47
    ValueStyle
    -0.46
     grin
    -0.45
    scrollY
    -0.44
     Editors
    -0.44
    }}}
    -0.43
    ')))
    -0.43
    "]').
    -0.42
    POSITIVE LOGITS
     ویکی‌پدی
    0.78
     doInBackground
    0.78
    InstrumentedTest
    0.74
     оригіналу
    0.74
    Geplaatst
    0.69
    Datuak
    0.68
     ویکی‌پدیا
    0.68
     linkovi
    0.67
    الإنجليزية
    0.65
    berdayakan
    0.63
    Activations Density 0.002%

    No Known Activations