© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 422
    Prev
    Next
    INDEX
    Explanations

    references to athletic performance and competition

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

    sports, times, and championships

    np_acts-logits-general · gemini-2.0-flash

    athletic events and best times

    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
     motors
    -0.34
     moteur
    -0.33
    heitsbild
    -0.30
    бов
    -0.30
    ✭✭
    -0.29
     sementes
    -0.29
     carnes
    -0.29
     nyel
    -0.29
     zub
    -0.28
    만
    -0.28
    POSITIVE LOGITS
    bcryptjs
    0.67
    msgTypes
    0.59
     المعيارى
    0.58
    oa̍t
    0.56
    MockMvc
    0.52
    Notae
    0.52
    InputBorder
    0.52
    Бахар
    0.50
    tagext
    0.50
     '\\;'
    0.50
    Activations Density 0.081%

    No Known Activations