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. 0-GEMMASCOPE-RES-16K
    6. 6374
    Prev
    Next
    INDEX
    Explanations

    references to size, specifically smaller objects or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beyond
    -0.57
     beyond
    -0.54
     BEYOND
    -0.53
     true
    -0.52
     gameObject
    -0.52
    >|</
    -0.51
     تض
    -0.51
     dir
    -0.51
    Beyond
    -0.51
     mena
    -0.51
    POSITIVE LOGITS
     simpler
    1.19
     cheaper
    1.13
     easier
    1.08
     shorter
    1.01
     lesser
    1.00
     safer
    0.94
    easier
    0.94
     Cheaper
    0.94
     slower
    0.87
     Easier
    0.86
    Activations Density 0.320%

    No Known Activations