© 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. 18-GEMMASCOPE-RES-16K
    11. 3506
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical representations

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

    Numbers within parentheses

    np_acts-logits-general · gemini-2.0-flash

    numbers and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smaller
    -0.82
     Smaller
    -0.79
     decreasing
    -0.79
     reduced
    -0.78
    Smaller
    -0.78
     low
    -0.76
     Reduced
    -0.76
     decreased
    -0.74
     Less
    -0.74
     less
    -0.74
    POSITIVE LOGITS
    (++
    0.81
    mybatisplus
    0.77
     exceeds
    0.69
     higher
    0.68
     whopping
    0.67
     exceed
    0.66
    [++
    0.65
     élevé
    0.65
    delà
    0.64
    выше
    0.64
    Activations Density 0.504%

    No Known Activations