© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4956
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions within biological or ecological systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    стота
    -0.37
     previews
    -0.37
     conven
    -0.37
     eléctricas
    -0.36
     Unto
    -0.35
    jiro
    -0.35
    try
    -0.34
     solos
    -0.34
    Alerts
    -0.34
    esthes
    -0.34
    POSITIVE LOGITS
    rrggbb
    0.85
    InjectAttribute
    0.84
    MessageTagHelper
    0.78
    mybatisplus
    0.73
    SharedDtor
    0.72
    الإنجليزية
    0.71
     الحره
    0.67
    styleable
    0.67
    CloseOperation
    0.65
     старости
    0.64
    Activations Density 0.539%

    No Known Activations