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. 129925
    Prev
    Next
    INDEX
    Explanations

    numerical values or codes often related to contact information or service details

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

    telephone numbers

    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
     inter
    -0.41
     propOrder
    -0.38
     Asian
    -0.38
    >",
    
    -0.37
    ม้
    -0.34
     search
    -0.34
    prüfung
    -0.34
     piggy
    -0.34
     ménage
    -0.33
     muse
    -0.33
    POSITIVE LOGITS
    OGND
    0.58
    CppMethod
    0.54
     AssemblyCompany
    0.54
     Biôgrafia
    0.50
    sizeCache
    0.50
    rungsseite
    0.49
    webElementXpaths
    0.49
    protoimpl
    0.48
    뀜
    0.47
    ItemBackground
    0.47
    Activations Density 0.003%

    No Known Activations