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. 112
    Prev
    Next
    INDEX
    Explanations

    information regarding medical guidelines and safety for a specific drug

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

    sections of text dealing with technical or specific information, especially related to medical, demographic, or rating contexts.

    oai_token-act-pair · gpt-4oTriggered by @timna
    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
    Geplaatst
    -0.55
     بتاريخ
    -0.52
    PyExc
    -0.51
    Viitteet
    -0.49
     FontWeight
    -0.48
     Lightboxes
    -0.48
    temming
    -0.48
    EndContext
    -0.47
    Subview
    -0.45
     count
    -0.44
    POSITIVE LOGITS
     VIAF
    0.65
     StatefulWidget
    0.62
    VIAF
    0.61
    PullParser
    0.61
     Autorisations
    0.58
     skrevet
    0.58
    "]();
    0.57
    ulative
    0.57
     /\.(
    0.57
     StatelessWidget
    0.56
    Activations Density 0.433%

    No Known Activations