© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11725
    Prev
    Next
    INDEX
    Explanations

    references to time-related delays or lateness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.44
    Rohy
    -0.39
    EndInit
    -0.39
    tagext
    -0.36
    ężczy
    -0.35
     BorderSide
    -0.35
     pinulongan
    -0.34
    Geplaatst
    -0.34
     tron
    -0.33
    eare
    -0.32
    POSITIVE LOGITS
     late
    3.08
     delayed
    2.81
     delay
    2.73
     Late
    2.63
    Late
    2.61
     LATE
    2.55
    late
    2.53
     Delayed
    2.45
     Delay
    2.44
     DELAY
    2.36
    Activations Density 0.943%

    No Known Activations