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. 21-GEMMASCOPE-RES-16K
    6. 281
    Prev
    Next
    INDEX
    Explanations

    references to success and outstanding performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.86
     الحره
    -0.76
    ftagPool
    -0.72
    曖昧さ回避
    -0.68
     виправивши
    -0.67
     NSCoder
    -0.66
    تفصیلات
    -0.61
    SafeArea
    -0.60
    
    -0.58
    gamos
    -0.57
    POSITIVE LOGITS
     teammates
    0.82
     leadership
    0.69
     locker
    0.69
     character
    0.68
    AndEndTag
    0.66
     culture
    0.66
     brotherhood
    0.65
     mentality
    0.64
     discipline
    0.62
     professionalism
    0.61
    Activations Density 0.155%

    No Known Activations