© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35234
    Prev
    Next
    INDEX
    Explanations

    the word "borne" in various contexts, particularly relating to transmission or causation

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

    disease or pathogen borne

    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
    Not in Any Lists

    No Comments

    Negative Logits
     sánchez
    -0.64
    Viitteet
    -0.59
     plufieurs
    -0.58
     ainfi
    -0.57
     málaga
    -0.57
    endregion
    -0.57
    ThroughAttribute
    -0.56
     lópez
    -0.56
     Felic
    -0.56
     مشين
    -0.56
    POSITIVE LOGITS
    borne
    2.73
     borne
    2.25
     Borne
    1.87
    bourne
    1.45
    born
    1.34
     born
    1.21
     Born
    1.21
    Born
    1.14
    BOURNE
    1.14
    BORN
    1.13
    Activations Density 0.006%

    No Known Activations