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. 20-GEMMASCOPE-RES-16K
    6. 7627
    Prev
    Next
    INDEX
    Explanations

    key metrics and statistics related to death rates and causes of death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advanced
    -0.69
    advance
    -0.68
     advance
    -0.68
    advanced
    -0.64
     Advance
    -0.61
    Advanced
    -0.59
     Advanced
    -0.59
     ADVANCE
    -0.58
    Advance
    -0.57
    цездатний
    -0.55
    POSITIVE LOGITS
     behind
    2.48
    behind
    2.23
     Behind
    2.13
    Behind
    2.05
     derrière
    1.99
     BEHIND
    1.98
     detrás
    1.86
     dietro
    1.75
     atrás
    1.51
     bakom
    1.47
    Activations Density 0.165%

    No Known Activations