© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 743
    Prev
    Next
    INDEX
    Explanations

    contextual markers, particularly the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     likewise
    -0.77
     also
    -0.69
     either
    -0.66
     addirittura
    -0.63
     medesimo
    -0.57
     justement
    -0.56
     également
    -0.55
     notizia
    -0.55
     nemlig
    -0.55
     zowel
    -0.54
    POSITIVE LOGITS
    ніципалі
    0.84
     ITIS
    0.82
    ंदीखरीदारी
    0.82
    ("")]
    
    0.79
    addCriterion
    0.75
    省市镇
    0.73
    httphttps
    0.73
    &=&\
    0.69
     Related
    0.69
    hanced
    0.68
    Activations Density 0.248%

    No Known Activations