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. 3-GEMMASCOPE-RES-16K
    6. 11135
    Prev
    Next
    INDEX
    Explanations

    references to prime ministers and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.74
     NSCoder
    -0.72
     gustó
    -0.68
     Josie
    -0.67
     guste
    -0.64
    ellees
    -0.64
    posób
    -0.64
     AssemblyTitle
    -0.63
     zucchero
    -0.63
    DropColumn
    -0.62
    POSITIVE LOGITS
     Prime
    3.04
     prime
    3.03
    Prime
    2.81
     PRIME
    2.71
    PRIME
    2.50
    prime
    2.38
     primes
    2.19
    primes
    1.98
    Primes
    1.89
     PRIM
    1.49
    Activations Density 0.087%

    No Known Activations