© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4971
    Prev
    Next
    INDEX
    Explanations

    elements related to delays and timing issues in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lateness or delays

    np_acts-logits-general · gemini-2.0-flash

    delay or lateness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irchen
    -0.62
    ModelMap
    -0.59
     unsubscribe
    -0.51
    Plural
    -0.50
    اظ
    -0.50
     MyBatis
    -0.49
     userSchema
    -0.49
    otry
    -0.49
    ToRemove
    -0.48
     transferable
    -0.46
    POSITIVE LOGITS
     delay
    2.76
     delayed
    2.62
     delays
    2.47
     Delay
    2.33
     delaying
    2.29
     DELAY
    2.27
    delay
    2.27
     Delayed
    2.26
    delayed
    2.21
    Delay
    2.13
    Activations Density 0.625%

    No Known Activations