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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14869
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions and their usage in context

    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
     betweenstory
    -1.09
     NSCoder
    -0.80
    thâu
    -0.71
    церт
    -0.69
     Photocase
    -0.67
     насељу
    -0.65
     appelez
    -0.65
    таратура
    -0.64
    eradish
    -0.64
    kháu
    -0.64
    POSITIVE LOGITS
     which
    0.67
    たまた
    0.61
     δη
    0.60
     however
    0.57
     sì
    0.56
     despite
    0.55
     perhaps
    0.55
     although
    0.54
    In
    0.52
    
    0.52
    Activations Density 0.286%

    No Known Activations