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. 129898
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and wellness topics

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

    variety of

    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
     Seeder
    -0.53
    SharedDtor
    -0.53
    CppMethod
    -0.50
    HostException
    -0.49
    UnusedPrivate
    -0.47
     odkazy
    -0.47
     MainAxisSize
    -0.46
     חיצוניים
    -0.46
     ActionResult
    -0.46
    DockStyle
    -0.45
    POSITIVE LOGITS
    :✨
    0.52
    Außerdem
    0.46
    esanan
    0.41
    ölkerung
    0.40
     vœux
    0.40
    She
    0.40
    hésite
    0.40
     pitié
    0.39
    Author
    0.39
     penyel
    0.38
    Activations Density 0.004%

    No Known Activations