© 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. 8941
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" in various tenses

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

    "was" followed by adverbs of time/place

    np_acts-logits-general · gemini-2.0-flash

    past origins and states

    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
    Currently
    -0.79
    currently
    -0.77
    now
    -0.75
     actuelles
    -0.75
     Sekarang
    -0.73
    woordig
    -0.72
     Currently
    -0.72
     atualmente
    -0.71
     attualmente
    -0.71
     currently
    -0.67
    POSITIVE LOGITS
     originally
    1.46
     previously
    1.32
     originalmente
    1.12
     initially
    1.10
     autrefois
    1.09
    originally
    1.08
     ursprünglich
    1.06
     recently
    1.01
     formerly
    0.99
     Originally
    0.99
    Activations Density 0.583%

    No Known Activations