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. 0-GEMMASCOPE-RES-16K
    6. 6801
    Prev
    Next
    INDEX
    Explanations

    terms related to drainage and the condition of drains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asional
    -0.54
    (''),
    -0.53
     minor
    -0.52
    imageshack
    -0.52
    jspx
    -0.51
    FormTagHelper
    -0.49
    (""));
    -0.49
    ']))
    
    -0.49
    ("");
    
    -0.48
    addComponent
    -0.47
    POSITIVE LOGITS
     drains
    1.06
     Drain
    1.06
     drain
    1.04
     draining
    1.02
    Drain
    0.92
    drain
    0.91
    Portail
    0.88
     clarity
    0.83
     drained
    0.82
     DRAIN
    0.79
    Activations Density 0.059%

    No Known Activations