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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13253
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the concept of something being great or excellent

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

    Preceding "source," "many," "way," "article," "grandmother," etc., with "great"

    np_acts-logits-general · gemini-2.0-flash

    great and good usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iség
    -0.53
     Lining
    -0.53
     labourers
    -0.52
    mlink
    -0.51
    ⟬
    -0.49
     islanders
    -0.49
    Televis
    -0.48
     Limb
    -0.48
    mancy
    -0.48
     chloroform
    -0.47
    POSITIVE LOGITS
    great
    1.27
     great
    1.19
    Great
    1.14
     GREAT
    1.09
     Great
    1.09
    GREAT
    1.07
    TheGreat
    0.80
    greatest
    0.71
     good
    0.69
     GOOD
    0.69
    Activations Density 0.041%

    No Known Activations