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. 117334
    Prev
    Next
    INDEX
    Explanations

    references to spouses and family 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
     времен
    -0.40
    principalColumn
    -0.39
    zepam
    -0.38
    UPI
    -0.37
     aborted
    -0.36
    şti
    -0.36
    olateral
    -0.35
     tijds
    -0.35
    TextSpan
    -0.35
     linking
    -0.35
    POSITIVE LOGITS
    énario
    0.60
    ⤹
    0.55
     AssemblyCompany
    0.51
     صوتيه
    0.50
     Administrativna
    0.50
    
    0.47
    tonsoft
    0.47
     للاسماء
    0.47
    ➟
    0.47
     disambiguazione
    0.45
    Activations Density 0.022%

    No Known Activations