© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7005
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or sequences in alphanumeric sequences, particularly in the context of URLs or encoded data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vermelhas
    -0.61
     BrowserModule
    -0.55
     atlik
    -0.53
     brancas
    -0.52
     privadas
    -0.47
    Iter
    -0.47
     privados
    -0.47
     záz
    -0.46
     amarillas
    -0.46
     COD
    -0.45
    POSITIVE LOGITS
     ligiloj
    0.75
    Clik
    0.69
    MLLoader
    0.68
    SourceChecksum
    0.68
     فريبيس
    0.68
    Autoritní
    0.67
    BeginInit
    0.62
     initComponents
    0.62
    EnableWeb
    0.62
    بوابة
    0.62
    Activations Density 0.399%

    No Known Activations