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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 257
    Prev
    Next
    INDEX
    Explanations

    the keyword "after" and variations in the context of sequences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Starts with A group
    after

    No Comments

    Negative Logits
     Theſe
    -1.41
     myſelf
    -1.35
     ſtate
    -1.30
     purpoſe
    -1.28
     leaſt
    -1.26
     Jefus
    -1.25
     pleaſure
    -1.24
     houſe
    -1.23
     Efq
    -1.22
     Houſe
    -1.19
    POSITIVE LOGITS
     after
    3.03
    after
    2.55
     After
    2.39
    After
    2.31
     dopo
    2.27
     après
    2.25
     após
    2.10
     AFTER
    2.04
     setelah
    1.94
     после
    1.91
    Activations Density 0.235%

    No Known Activations