© 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. 2995
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures

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

    Past tense auxiliary verbs ("had", "was", "were")

    np_acts-logits-general · gemini-2.0-flash

    past events by a certain time

    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
     оригіналу
    -0.79
     selama
    -0.62
    illier
    -0.58
    epik
    -0.56
    cinogenicity
    -0.53
    bitat
    -0.53
     همیشه
    -0.50
     مواليد
    -0.49
     nahilalakip
    -0.49
    InSection
    -0.48
    POSITIVE LOGITS
     still
    1.19
     already
    1.19
     hadn
    1.09
    still
    1.07
    already
    1.02
    すでに
    1.00
    既に
    0.98
     Already
    0.98
    Still
    0.96
     had
    0.96
    Activations Density 0.563%

    No Known Activations