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. 20-GEMMASCOPE-RES-131K
    6. 22429
    Prev
    Next
    INDEX
    Explanations

    the presence of funding mechanisms or support for projects

    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_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.69
     mergeFrom
    -0.60
     censiti
    -0.57
     autorytatywna
    -0.56
    Controllo
    -0.54
    vician
    -0.54
    ècie
    -0.54
     Walkover
    -0.54
    __":
    
    -0.53
     BrowserModule
    -0.52
    POSITIVE LOGITS
     msglen
    0.33
     batteries
    0.33
     electric
    0.33
     eléctrica
    0.29
     voltage
    0.29
     elektry
    0.28
     Volta
    0.28
     elettrica
    0.26
     է
    0.26
     baterai
    0.26
    Activations Density 0.087%

    No Known Activations