© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1309
    Prev
    Next
    INDEX
    Explanations

    scientific and mathematical variables or terms

    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
     Mili
    -0.88
    Mili
    -0.73
     Bouchard
    -0.68
    ocie
    -0.68
     Anja
    -0.67
    mili
    -0.67
     Spie
    -0.66
     Sait
    -0.66
     Ostro
    -0.65
    ie
    -0.63
    POSITIVE LOGITS
     Jamestown
    0.80
     ujednoznacz
    0.79
     McCarthy
    0.77
     Punta
    0.70
     dama
    0.69
     Oswald
    0.65
     Shen
    0.63
    Shen
    0.62
     Hawthorne
    0.62
    Adobe
    0.62
    Activations Density 2.019%

    No Known Activations