Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 15612
    Prev
    Next
    INDEX
    Explanations

    references to conditional statements and comparisons in scientific discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    WaitGroup
    -0.64
     comets
    -0.56
     FetchType
    -0.54
    веси
    -0.52
    faker
    -0.52
     Bezir
    -0.50
     مشين
    -0.50
    awaiter
    -0.50
     Hauptmann
    -0.49
    Stopping
    -0.49
    POSITIVE LOGITS
     محفوظة
    0.77
     دیکھیے
    0.63
    BeginContext
    0.62
    sizeCache
    0.61
     icke
    0.59
     illetve
    0.57
     *)&
    0.56
    ouille
    0.56
    المشاركات
    0.55
    rouvez
    0.55
    Activations Density 0.498%

    No Known Activations