© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 6050
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers representing data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.76
     WebApplication
    -0.75
     MessageBoxIcon
    -0.74
    DockStyle
    -0.74
    Autoritní
    -0.74
    RegressionTest
    -0.73
     MacGregor
    -0.71
     Wann
    -0.70
    hastly
    -0.69
    JspWriter
    -0.67
    POSITIVE LOGITS
    elfth
    0.88
    Twelve
    0.83
    6
    0.80
     ۱۲
    0.78
    twelve
    0.78
    ۱۲
    0.78
     Twelve
    0.76
     twelve
    0.72
    2
    0.70
     zwölf
    0.67
    Activations Density 0.338%

    No Known Activations