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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92444
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Smith"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    routeProvider
    -0.67
    </>
    
    -0.63
     otomatig
    -0.59
     relegated
    -0.58
     Brag
    -0.57
    kurt
    -0.57
     Pelleg
    -0.55
    oredCriteria
    -0.55
     Rag
    -0.55
     ***!
    -0.55
    POSITIVE LOGITS
     Smith
    1.16
    Smith
    1.15
     SMITH
    1.00
     smith
    0.98
    smith
    0.94
     Smiths
    0.91
    SMITH
    0.84
     Masyarakat
    0.68
     présidenti
    0.63
     Putih
    0.61
    Activations Density 0.008%

    No Known Activations