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. 4683
    Prev
    Next
    INDEX
    Explanations

    phrases related to exchanges and conversations

    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
     specific
    -0.55
     @
    -0.43
     autorytatywna
    -0.43
    uten
    -0.41
     us
    -0.41
    mä
    -0.41
    รม
    -0.41
     Specific
    -0.41
     {
    -0.41
    下さ
    -0.40
    POSITIVE LOGITS
     itſelf
    0.87
    BeginInit
    0.86
     myſelf
    0.84
     initWithFrame
    0.84
     himſelf
    0.79
     EconPapers
    0.79
     Referential
    0.78
     reaſon
    0.77
     chofe
    0.75
     '\\;'
    0.75
    Activations Density 0.438%

    No Known Activations