© 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. 23-GEMMASCOPE-RES-16K
    11. 9360
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the occurrence of events or actions over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tomorrow
    -0.61
     futuras
    -0.58
     demain
    -0.55
    HtmlAttribute
    -0.55
     venganza
    -0.54
     mahdollis
    -0.53
     prochaines
    -0.53
     przysz
    -0.52
    tomorrow
    -0.52
     thyself
    -0.51
    POSITIVE LOGITS
     unsuccessful
    1.21
     successful
    1.20
     years
    1.14
     lengthy
    1.09
    successful
    1.03
     months
    1.02
     failed
    1.00
    Successful
    0.96
     extensive
    0.95
     decades
    0.93
    Activations Density 0.382%

    No Known Activations