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. 22-GEMMASCOPE-RES-16K
    6. 14024
    Prev
    Next
    INDEX
    Explanations

    words related to sports performance and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Eloquent
    -0.48
    DockStyle
    -0.45
    /*!
    -0.41
    IsTrue
    -0.41
    utnik
    -0.40
     prevede
    -0.40
    maktadır
    -0.39
     länder
    -0.39
     fullt
    -0.39
     PhpStorm
    -0.39
    POSITIVE LOGITS
     performance
    1.26
     performances
    1.20
     showing
    1.01
    performance
    0.96
     outing
    0.89
    showing
    0.89
     desempeño
    0.86
     effort
    0.86
     run
    0.84
     PERFORMANCE
    0.84
    Activations Density 0.209%

    No Known Activations