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. 130997
    Prev
    Next
    INDEX
    Explanations

    references to the word "tan" and its variations in different contexts

    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
    rungsseite
    -0.72
    ThroughAttribute
    -0.60
    VersionUID
    -0.59
     Obrador
    -0.58
     Ophelia
    -0.57
     otomatig
    -0.57
     Amigo
    -0.56
    躇
    -0.56
    plings
    -0.55
    asie
    -0.55
    POSITIVE LOGITS
     Tan
    0.91
    Tan
    0.83
     TAN
    0.77
     Tanner
    0.74
     tan
    0.70
     Tanaka
    0.67
    Tanner
    0.60
     Tanja
    0.59
     tanning
    0.56
     تان
    0.56
    Activations Density 0.007%

    No Known Activations