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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 12884
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to caregiving and managing infant-related tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capital
    -0.51
     shipwreck
    -0.49
    focusable
    -0.49
     reagiert
    -0.48
     CONTAIN
    -0.46
     wealth
    -0.46
    Financing
    -0.44
     suppressed
    -0.44
     الدرا
    -0.43
    ikiran
    -0.43
    POSITIVE LOGITS
    manual
    0.76
     manually
    0.75
     manual
    0.74
     manuale
    0.73
    Manual
    0.69
    Manually
    0.68
     manuelle
    0.66
     manualmente
    0.65
     manuell
    0.64
     Manually
    0.61
    Activations Density 0.462%

    No Known Activations