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. 8-GEMMASCOPE-RES-16K
    6. 8616
    Prev
    Next
    INDEX
    Explanations

    technical terminology and details relating to engines and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exhi
    -0.53
    HomeAsUpEnabled
    -0.53
     anch
    -0.53
    "}")
    -0.53
    ollectionView
    -0.52
     CHtml
    -0.51
     Conservancy
    -0.49
    basicConfig
    -0.49
    \)
    -0.47
     ungu
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.76
    ItemBackground
    0.64
     noires
    0.63
    MessageTagHelper
    0.61
     producteurs
    0.57
     Normdatei
    0.56
    featureID
    0.56
     piattaforma
    0.55
     sauvages
    0.55
    panou
    0.54
    Activations Density 0.197%

    No Known Activations