© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6003
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their unique characteristics or experiences

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

    occurrences of the word "individual" or phrases related to individual characteristics.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambién
    -0.60
    étoit
    -0.59
    vänt
    -0.56
    Pranala
    -0.53
    etchup
    -0.52
     vacuna
    -0.51
    pecabe
    -0.51
    Fordítás
    -0.51
     nemico
    -0.51
     BeautifulSoup
    -0.50
    POSITIVE LOGITS
     individual
    1.32
     Individual
    1.27
    Individual
    1.23
    individual
    1.21
     INDIVIDUAL
    1.10
    ividual
    1.04
    IVIDUAL
    0.99
     individuals
    0.95
     Individuals
    0.94
    Individuals
    0.90
    Activations Density 0.031%

    No Known Activations