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. 21-GEMMASCOPE-RES-16K
    6. 7075
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory compliance and automotive performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probably
    -0.98
     Apparently
    -0.96
     stuff
    -0.94
    Apparently
    -0.93
    Basically
    -0.92
     Basically
    -0.90
    apparently
    -0.89
     Probably
    -0.89
     maybe
    -0.88
     basically
    -0.86
    POSITIVE LOGITS
     leveraging
    0.86
    . 
    0.78
     showcasing
    0.77
     impactful
    0.71
     featuring
    0.70
     utilizing
    0.69
     showcased
    0.69
     impacting
    0.68
     unveiled
    0.68
     launching
    0.68
    Activations Density 0.289%

    No Known Activations