© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1452
    Prev
    Next
    INDEX
    Explanations

    the word "thus" and its variations, often indicating a conclusion or result

    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
     Bernadette
    -0.77
     Coton
    -0.75
     devils
    -0.73
     LON
    -0.73
    intree
    -0.73
     Frankie
    -0.72
     Apre
    -0.72
    eable
    -0.71
     Fara
    -0.70
     Eureka
    -0.70
    POSITIVE LOGITS
     thus
    2.46
     Thus
    2.38
    Thus
    2.37
    thus
    2.17
    Ainsi
    1.62
     Ainsi
    1.57
     ainsi
    1.25
     således
    1.24
     así
    1.23
     astfel
    1.23
    Activations Density 0.061%

    No Known Activations