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. 8648
    Prev
    Next
    INDEX
    Explanations

    discourse markers indicating contrast or opposition

    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
     समीक्षाओं
    -0.66
     Akismet
    -0.63
    ंदीखरीदारी
    -0.61
    ialmente
    -0.60
     internetowa
    -0.58
     contextLoads
    -0.58
     magasiner
    -0.55
     Waray
    -0.54
    ^(@)
    -0.54
    цездатний
    -0.53
    POSITIVE LOGITS
    WithIOException
    0.61
    ChildScrollView
    0.59
     hence
    0.59
    hence
    0.56
     whereas
    0.55
     although
    0.55
     however
    0.53
     поэтому
    0.53
     "..\..\
    0.53
     wherefore
    0.52
    Activations Density 1.005%

    No Known Activations