Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 102670
    Prev
    Next
    INDEX
    Explanations

    references to plastic bags and waste management

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

    synthetic materials and containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imanapun
    -0.33
    DaoImpl
    -0.31
     segmento
    -0.29
     Desenvolvimento
    -0.28
     HOL
    -0.28
     conceito
    -0.28
     maxn
    -0.28
    EventManager
    -0.27
     kontra
    -0.27
    pgterms
    -0.27
    POSITIVE LOGITS
    :✨
    0.62
    ">//
    0.62
    rungsseite
    0.55
     EconPapers
    0.52
    vellous
    0.51
     Waſſer
    0.50
    
    0.50
    MENAFN
    0.50
     <<<<<<<<<<<<<<
    0.50
     BrowserModule
    0.50
    Activations Density 0.015%

    No Known Activations