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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 3019
    Prev
    Next
    INDEX
    Explanations

    terms related to growth and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
                    
    -0.70
    Sia
    -0.61
     }^{[
    -0.61
     paio
    -0.60
     tinnitus
    -0.60
     Rabin
    -0.59
    tabol
    -0.59
     Melville
    -0.59
     sencillas
    -0.59
     alertDialog
    -0.59
    POSITIVE LOGITS
     GROW
    1.86
    GROW
    1.71
     Grow
    1.68
    grow
    1.66
     grow
    1.63
    Grow
    1.59
     grows
    1.57
     growing
    1.50
    growing
    1.44
     grew
    1.42
    Activations Density 0.053%

    No Known Activations