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. 32-GEMMASCOPE-RES-131K
    6. 129884
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare service and volunteer support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    our mission is to provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chops
    -0.60
    úgó
    -0.57
     downsides
    -0.56
     المعيارى
    -0.56
    ckså
    -0.55
     tropes
    -0.54
     thorny
    -0.54
    Quite
    -0.54
     loopholes
    -0.54
     Quite
    -0.52
    POSITIVE LOGITS
    是我们
    0.43
    NOWLEDGE
    0.42
     integrated
    0.41
     inspired
    0.40
    私たちは
    0.40
     continuously
    0.39
    我们是
    0.37
     poprzez
    0.37
     committed
    0.36
     spiritual
    0.36
    Activations Density 0.028%

    No Known Activations