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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8172
    Prev
    Next
    INDEX
    Explanations

    references to casualties and fatalities in violent or tragic events

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

    Reports of deaths or injuries

    np_acts-logits-general · gemini-2.0-flash

    killed and injured people

    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
     betweenstory
    -0.62
    
    -0.54
    tagHelperRunner
    -0.54
    MessageOf
    -0.50
     препратки
    -0.49
    تقاوى
    -0.44
    GeoNames
    -0.42
     shade
    -0.42
    AndroidJUnit
    -0.42
    Хьажоргаш
    -0.41
    POSITIVE LOGITS
     dilaporkan
    0.51
     victims
    0.49
    死者
    0.47
     casualties
    0.47
    多人
    0.46
     ainfi
    0.45
    ésult
    0.45
     addUser
    0.44
     victimes
    0.42
     injured
    0.41
    Activations Density 0.177%

    No Known Activations