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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15379
    Prev
    Next
    INDEX
    Explanations

    phrases related to women's professional motocross and associated organizations

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

    after company names/acronyms

    np_acts-logits-general · gemini-2.0-flash

    global markets and leading industries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.77
    ChildScrollView
    -0.72
     المعيارى
    -0.65
     Савезне
    -0.59
    GIVEREF
    -0.59
     demografica
    -0.56
    SourceChecksum
    -0.52
    曖昧さ回避
    -0.49
    lapsingToolbar
    -0.48
    BeginInit
    -0.48
    POSITIVE LOGITS
    VersionUID
    0.45
     pediatric
    0.37
     relatifs
    0.37
     européennes
    0.37
     terecht
    0.36
     québéco
    0.35
     beschäftigen
    0.35
    国産
    0.35
     homemade
    0.34
     współ
    0.34
    Activations Density 1.231%

    No Known Activations