© 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. 22-GEMMASCOPE-RES-16K
    11. 10662
    Prev
    Next
    INDEX
    Explanations

    instances referring to ongoing situations or actions in the present context

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

    Follows "now" or "currently"

    np_acts-logits-general · gemini-2.0-flash

    current moment

    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
     then
    -1.29
     previously
    -1.09
     ранее
    -1.04
     initially
    -1.03
     originally
    -1.03
    then
    -1.01
     awalnya
    -0.96
     sebelumnya
    -0.95
     lately
    -0.94
    originally
    -0.94
    POSITIVE LOGITS
    weer
    0.68
     unrecogn
    0.65
     regret
    0.62
    Regret
    0.61
     gili
    0.60
     regrets
    0.59
    に至
    0.57
    seks
    0.56
    すっかり
    0.56
    værende
    0.54
    Activations Density 0.301%

    No Known Activations