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. 13295
    Prev
    Next
    INDEX
    Explanations

    phrases indicating historical actions or events related to significant occurrences

    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
    étaire
    -0.65
    atchewan
    -0.61
    fromJson
    -0.58
    emony
    -0.58
    ibouti
    -0.57
    onesia
    -0.57
    Хро
    -0.56
    ardless
    -0.55
    cephala
    -0.55
     actuelles
    -0.55
    POSITIVE LOGITS
     earlier
    1.21
    earlier
    1.03
    Earlier
    0.93
     hadn
    0.92
     Earlier
    0.90
     hoped
    0.89
    mişti
    0.86
     previously
    0.85
     disambiguazione
    0.83
    esModule
    0.82
    Activations Density 0.306%

    No Known Activations