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. 23-GEMMASCOPE-RES-131K
    6. 23229
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to financial advice and debt management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.69
    contentLoaded
    -0.58
    AntiForgeryToken
    -0.52
    
    -0.51
    новништво
    -0.50
    Hauptartikel
    -0.49
    ViewFeatures
    -0.48
    parsedMessage
    -0.47
     poveznice
    -0.46
    spyOn
    -0.46
    POSITIVE LOGITS
    ...@
    0.46
     Secrétaire
    0.37
    appartamento
    0.35
     erb
    0.35
    associazione
    0.35
    オル
    0.34
    sidemargin
    0.34
    
    0.34
     година
    0.34
     Envío
    0.34
    Activations Density 0.176%

    No Known Activations