© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4875
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to significant achievements and advancements

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

    Positive adjectives after intensifiers

    np_acts-logits-general · gemini-2.0-flash

    words of extreme praise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -1.05
    AndEndTag
    -0.75
     kaarangay
    -0.68
    存于互联网档案馆
    -0.66
    __*/
    -0.65
    
    -0.64
    posedge
    -0.63
     समीक्षाओं
    -0.58
     Certo
    -0.58
    Interesting
    -0.57
    POSITIVE LOGITS
     unbelievable
    1.22
     incredible
    1.21
     phenomenal
    1.18
     extraordinary
    1.16
     astonishing
    1.15
     astounding
    1.14
     staggering
    1.08
     amazing
    1.07
     unparalleled
    1.05
     breathtaking
    1.01
    Activations Density 0.358%

    No Known Activations