Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15715
    Prev
    Next
    INDEX
    Explanations

    references to martial arts and fighting techniques

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

    Martial arts styles or combat

    np_acts-logits-general · gemini-2.0-flash

    martial arts and fighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terraform
    -0.39
     cdti
    -0.38
    JsonPropertyName
    -0.37
     sezon
    -0.36
    opardi
    -0.35
    GLFW
    -0.35
     ODI
    -0.34
     שוליים
    -0.34
     MNRAS
    -0.34
    Carex
    -0.34
    POSITIVE LOGITS
     martial
    1.53
     Martial
    1.23
    martial
    1.22
    Martial
    1.15
     karate
    1.15
     Karate
    1.05
    🥋
    1.01
     dojo
    0.88
     sparring
    0.85
    ekwondo
    0.84
    Activations Density 0.084%

    No Known Activations