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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 360
    Prev
    Next
    INDEX
    Explanations

    events related to the career progression of a football player

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

    Prepositions followed by city names

    np_acts-logits-general · gemini-2.0-flash

    team names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ‚¬
    -0.68
    MetaObject
    -0.60
    
    -0.57
    PINES
    -0.56
    ArrowToggle
    -0.56
     Rhapsody
    -0.56
    onViewCreated
    -0.55
     referrerpolicy
    -0.55
    Demografía
    -0.54
     MotionEvent
    -0.53
    POSITIVE LOGITS
     lenker
    0.53
    phrine
    0.52
     acu
    0.49
     ex
    0.48
     promotion
    0.47
     City
    0.47
     betweenstory
    0.47
    retario
    0.44
    áról
    0.44
    انيف
    0.44
    Activations Density 0.111%

    No Known Activations