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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 130947
    Prev
    Next
    INDEX
    Explanations

    instances of the term "afterwards" or similar variations, indicating a focus on subsequent events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lccn
    -0.55
    boutin
    -0.52
    cupertino
    -0.51
    뀜
    -0.51
    SqlDataReader
    -0.50
     vectorstock
    -0.50
     Jefus
    -0.50
    IsContent
    -0.49
     sonnet
    -0.49
    enedor
    -0.48
    POSITIVE LOGITS
     afterwards
    0.84
    Afterwards
    0.73
     Afterwards
    0.73
     afterward
    0.71
     Afterward
    0.57
    Aftermath
    0.49
     חיצוניים
    0.47
     Hutchins
    0.47
     danach
    0.47
     BoxDecoration
    0.46
    Activations Density 0.008%

    No Known Activations