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
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15644
    Prev
    Next
    INDEX
    Explanations

    mathematical terminologies and symbols related to spaces and manifolds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Населення
    -0.47
    ร้อน
    -0.42
    aryen
    -0.37
    WEBPACK
    -0.36
    bake
    -0.36
     bụng
    -0.35
    nuclear
    -0.34
    cole
    -0.34
    汚
    -0.34
    hette
    -0.34
    POSITIVE LOGITS
     space
    0.60
    空間
    0.57
    
    0.56
    \|^{
    0.53
    空间
    0.52
     ruimte
    0.51
     Space
    0.51
    espace
    0.50
    <thead>
    0.50
    Xna
    0.49
    Activations Density 0.669%

    No Known Activations