© 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. 6726
    Prev
    Next
    INDEX
    Explanations

    statistical significance in comparisons and differences between groups

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

    Adverbs following forms of "to be."

    np_acts-logits-general · gemini-2.0-flash

    not significant, statistically significant

    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
    QMetaType
    -0.66
    SharedCtor
    -0.57
    UserScript
    -0.56
    __*/
    -0.55
     <=",
    -0.53
    出版年
    -0.52
    исленность
    -0.51
     favoritas
    -0.50
    HasAnnotation
    -0.50
    bukkit
    -0.50
    POSITIVE LOGITS
     unbelievable
    1.20
     astounding
    1.00
     unimaginable
    0.98
     staggering
    0.98
     incredible
    0.97
     astonishing
    0.92
    incredible
    0.89
     immeasurable
    0.87
     remarkable
    0.86
     indescribable
    0.86
    Activations Density 0.261%

    No Known Activations