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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1966
    Prev
    Next
    INDEX
    Explanations

    details about romantic relationships and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     myſelf
    -0.99
     itſelf
    -0.93
    ]--;
    -0.92
     Theſe
    -0.88
     himſelf
    -0.85
     Reſ
    -0.85
     Efq
    -0.84
     Majefty
    -0.82
     auffi
    -0.82
     iſt
    -0.82
    POSITIVE LOGITS
     boyfriend
    1.31
     girlfriend
    1.27
     dating
    1.19
     date
    1.05
     boyfriends
    1.01
     partner
    1.00
     ex
    0.99
     Dating
    0.98
     Boyfriend
    0.95
     Girlfriend
    0.95
    Activations Density 0.168%

    No Known Activations