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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 10561
    Prev
    Next
    INDEX
    Explanations

    instances of the word "amazing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    又要
    -0.63
     fondi
    -0.61
    paksa
    -0.59
    дован
    -0.58
    enni
    -0.58
    வு
    -0.58
     genellikle
    -0.57
    uyla
    -0.56
    tır
    -0.56
    Humor
    -0.56
    POSITIVE LOGITS
     amazing
    1.90
    amazing
    1.83
    Amazing
    1.73
     Amazing
    1.72
     incredible
    1.65
     AMAZING
    1.59
    AMAZING
    1.59
     Incredible
    1.40
    incredible
    1.40
     incredi
    1.38
    Activations Density 0.053%

    No Known Activations