© 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. 9514
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to electronic circuits and components

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

    Electricity, power, and related components/concepts

    np_acts-logits-general · gemini-2.0-flash

    electrical design and power circuits

    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
    IsMutable
    -0.80
    rrggbb
    -0.80
    Personendaten
    -0.78
    Билгалдахарш
    -0.76
     autorytatywna
    -0.76
     '\\;'
    -0.75
    AndEndTag
    -0.73
     EconPapers
    -0.72
     mizuno
    -0.72
     moratorium
    -0.70
    POSITIVE LOGITS
     power
    0.67
     proget
    0.63
     design
    0.62
     voltage
    0.60
     Power
    0.59
     circuitry
    0.59
     progettazione
    0.57
     electrical
    0.57
     electrically
    0.57
    power
    0.56
    Activations Density 1.490%

    No Known Activations