Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90049
    Prev
    Next
    INDEX
    Explanations

    references to family members and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     literario
    -0.37
    collants
    -0.36
    entière
    -0.36
    leby
    -0.35
     partielle
    -0.35
    prefixer
    -0.35
     titolata
    -0.35
     colgantes
    -0.35
    liferation
    -0.35
     Thriller
    -0.34
    POSITIVE LOGITS
     daddy
    0.92
     Daddy
    0.89
    Daddy
    0.81
     papa
    0.77
     grandpa
    0.73
     mommy
    0.73
     papà
    0.70
    Papa
    0.69
    Grandpa
    0.69
     Grandpa
    0.68
    Activations Density 0.009%

    No Known Activations