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. 25-GEMMASCOPE-RES-16K
    6. 5704
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high-quality manufacturing and customer commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLUYE
    -0.62
     fundos
    -0.51
    RefreshLayout
    -0.48
    uspiel
    -0.48
    Airbnb
    -0.47
    Margot
    -0.47
    WEBPACK
    -0.46
     tuyến
    -0.45
     Spotify
    -0.45
    SBATCH
    -0.45
    POSITIVE LOGITS
     distributors
    0.83
     distributor
    0.82
     sales
    0.80
     OEM
    0.79
     Engineered
    0.78
    sales
    0.75
     Distributor
    0.75
     aftermarket
    0.73
     Sales
    0.72
    Distributor
    0.70
    Activations Density 0.458%

    No Known Activations