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. 13-GEMMASCOPE-RES-16K
    6. 462
    Prev
    Next
    INDEX
    Explanations

    references to historical events and changes in protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    historical information about organizations and their transitions over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.66
     pekan
    -0.62
     săptăm
    -0.60
    liothèque
    -0.57
    ngdoc
    -0.57
     PhpStorm
    -0.55
    ulement
    -0.55
    CreateModel
    -0.55
     Kluwer
    -0.54
     Theſe
    -0.54
    POSITIVE LOGITS
     generations
    0.85
     successive
    0.72
     Generations
    0.66
    
    0.63
     succession
    0.62
     eras
    0.62
     vicissitudes
    0.58
     evolution
    0.57
     decades
    0.56
     Succ
    0.55
    Activations Density 0.381%

    No Known Activations