© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6293
    Prev
    Next
    INDEX
    Explanations

    references to dragons and dragon-related imagery

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

    dragons

    np_acts-logits-general · gemini-2.0-flash

    dragon, dragons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.55
    httphttps
    -0.53
    CrossRef
    -0.52
    bufio
    -0.52
    loem
    -0.49
    enumii
    -0.48
    __":
    -0.47
     utafitiHapana
    -0.47
    ReusableCell
    -0.47
    writeFieldEnd
    -0.47
    POSITIVE LOGITS
     dragon
    1.59
     Dragon
    1.49
     dragons
    1.41
    Dragon
    1.38
    dragon
    1.33
     DRAGON
    1.31
     Dragons
    1.26
     dragón
    1.25
    Dragons
    1.15
    龙
    1.02
    Activations Density 0.221%

    No Known Activations