Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8121
    Prev
    Next
    INDEX
    Explanations

    the phrase "anyway" and its variants, indicating a conversational or casual tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gwick
    -0.73
    SEGUIR
    -0.71
    ContentAsync
    -0.68
     fairest
    -0.66
    awtextra
    -0.64
    PhysRevD
    -0.63
    ModelAttribute
    -0.63
     RoutedEventArgs
    -0.60
     useEffect
    -0.60
    PhysRev
    -0.59
    POSITIVE LOGITS
     iNdEx
    0.53
    unknownFields
    0.51
    Chham
    0.50
     stanovnika
    0.50
     entry
    0.50
     kiin
    0.49
    Entry
    0.49
    Kay
    0.48
    괄
    0.48
     RSP
    0.47
    Activations Density 0.122%

    No Known Activations