© 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. 18-GEMMASCOPE-RES-16K
    11. 6768
    Prev
    Next
    INDEX
    Explanations

    numerical references to time or duration, particularly in years

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

    Punctuation, especially commas

    np_acts-logits-general · gemini-2.0-flash

    counting years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immediate
    -0.55
    不久
    -0.53
    Через
    -0.51
     soon
    -0.50
    immediate
    -0.50
     segera
    -0.50
    しばらく
    -0.50
     quick
    -0.49
     quickly
    -0.49
    多年
    -0.49
    POSITIVE LOGITS
    Datuak
    0.69
     culminating
    0.67
     uninterrupted
    0.63
    期间
    0.62
     culminated
    0.59
    ようやく
    0.58
    saraba
    0.58
     geslacht
    0.57
     Daarna
    0.57
     ModelRenderer
    0.56
    Activations Density 0.366%

    No Known Activations