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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8538
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" used to emphasize statements or transition between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    homonymie
    -0.50
    WebElementEntity
    -0.47
     jspb
    -0.47
     censiti
    -0.46
    úgó
    -0.45
    rakech
    -0.45
    Brainz
    -0.45
    httphttps
    -0.45
     curt
    -0.43
    arusian
    -0.42
    POSITIVE LOGITS
     So
    2.77
    So
    2.47
     所以
    1.17
     so
    1.05
     Então
    1.03
     Så
    0.98
     Со
    0.97
    所以
    0.94
     Entonces
    0.91
    Со
    0.90
    Activations Density 0.061%

    No Known Activations