© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 62162
    Prev
    Next
    INDEX
    Explanations

    instances of the word "encounter" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    coming across something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     GenerationType
    -0.75
    wiſe
    -0.68
     Мексичка
    -0.65
    存于互联网档案馆
    -0.65
    حياتها
    -0.61
    Spoljašnje
    -0.60
     imagui
    -0.58
     digress
    -0.57
    VIAF
    -0.57
    Pap
    -0.57
    POSITIVE LOGITS
     encounter
    1.82
    encounter
    1.80
     Encounter
    1.80
    Encounter
    1.76
     encountered
    1.73
     encounters
    1.70
     encountering
    1.49
     Encounters
    1.32
     Begegn
    1.02
    遭遇
    0.91
    Activations Density 0.004%

    No Known Activations