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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 4947
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and luck in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.85
     chopsticks
    -0.77
    RTEE
    -0.77
    ########.
    -0.73
     DPM
    -0.73
     Sarm
    -0.70
    mappedBy
    -0.70
     aught
    -0.69
     consecration
    -0.67
     posthum
    -0.67
    POSITIVE LOGITS
    好在
    0.88
    Fortunately
    0.84
    Thankfully
    0.82
    Luckily
    0.81
     Luckily
    0.79
     Thankfully
    0.78
     Fortunately
    0.78
    幸好
    0.75
     fortunately
    0.71
    ureusement
    0.65
    Activations Density 0.145%

    No Known Activations