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. 136
    Prev
    Next
    INDEX
    Explanations

    occurrences of opening parentheses or similar characters in code or expressions

    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
     فريبيس
    -0.73
     schia
    -0.58
     مُعرِّف
    -0.54
     Baillargeon
    -0.54
    遽
    -0.53
    constexpr
    -0.52
     advisory
    -0.52
     Dés
    -0.51
    بوابة
    -0.50
    anganese
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.83
    principalTable
    0.71
     ddelweddau
    0.64
    migrationBuilder
    0.60
    BeginContext
    0.58
     виправивши
    0.58
    @",
    0.57
     Vikipedi
    0.56
    elsif
    0.55
    enterOuterAlt
    0.54
    Activations Density 0.001%

    No Known Activations