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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 10759
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific or technical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.66
    ristas
    -0.49
     nahilalakip
    -0.47
     benefici
    -0.46
     minuta
    -0.45
    getHours
    -0.44
    phrag
    -0.43
    MessageTagHelper
    -0.43
    Rao
    -0.42
     veio
    -0.42
    POSITIVE LOGITS
    expandindo
    0.82
    MemoryWarning
    0.75
     kasarigan
    0.74
    __":
    
    0.68
     postIndex
    0.66
     Перейти
    0.65
    NUMX
    0.62
    XmlType
    0.61
    WebVitals
    0.61
     <<<<<<<<<<<<<<
    0.60
    Activations Density 0.306%

    No Known Activations