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. 11700
    Prev
    Next
    INDEX
    Explanations

    phrases related to the use and application of software or technology

    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
     McM
    -0.70
     commis
    -0.68
    Interv
    -0.68
    Nederlands
    -0.66
     McCarty
    -0.65
     Altman
    -0.63
     Biggs
    -0.63
    SPARENT
    -0.62
    Cached
    -0.62
     utopian
    -0.62
    POSITIVE LOGITS
    use
    1.12
     use
    0.94
    Use
    0.90
    Uso
    0.90
     Use
    0.86
    Vist
    0.81
     Uses
    0.81
     Vist
    0.81
     uso
    0.79
     InputDecoration
    0.78
    Activations Density 0.159%

    No Known Activations