© 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. 6567
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions involving measurements or comparisons

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

    Comes before words ending in "-ing" or "-ion"

    np_acts-logits-general · gemini-2.0-flash

    ladies and civilians

    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
     masculinos
    -0.59
     masculino
    -0.59
     männ
    -0.56
    loit
    -0.56
     băr
    -0.55
     chồng
    -0.53
     Männer
    -0.53
     suaminya
    -0.51
    Tembelea
    -0.50
     erkek
    -0.49
    POSITIVE LOGITS
     istrinya
    0.84
     Italijanski
    0.74
     civilian
    0.70
     womens
    0.69
    ladies
    0.69
     civilians
    0.68
     ladies
    0.67
    \{\\
    0.66
     madam
    0.66
    Ladies
    0.65
    Activations Density 1.465%

    No Known Activations