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. 15529
    Prev
    Next
    INDEX
    Explanations

    mentions of news outlets and their coverage in sports and finance

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

    Sports-related content and broadcasting

    np_acts-logits-general · gemini-2.0-flash
    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
    rungsseite
    -0.69
     Chwiliwch
    -0.60
    StoryboardSegue
    -0.59
     مشارکت‌کنندگان
    -0.56
    mybatisplus
    -0.56
    <?
    -0.56
    Geplaatst
    -0.54
    
    -0.54
    usermodel
    -0.54
     betweenstory
    -0.53
    POSITIVE LOGITS
     Sports
    1.02
     sports
    0.97
     ESPN
    0.93
    Sports
    0.90
    sports
    0.83
    ESPN
    0.78
     Sport
    0.76
     SPORTS
    0.74
    Sport
    0.73
     sport
    0.71
    Activations Density 0.121%

    No Known Activations