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. 16-GEMMASCOPE-RES-16K
    6. 2982
    Prev
    Next
    INDEX
    Explanations

    anatomical terms and descriptions related to the body's vascular or nervous systems

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

    Anatomical terms related to nerves and veins

    np_acts-logits-general · gemini-2.0-flash

    posterior anatomical locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.88
     Reſ
    -0.88
     myſelf
    -0.82
     Diſ
    -0.81
    сшта
    -0.80
     wrists
    -0.78
     Anſ
    -0.76
     unſ
    -0.75
     Houſe
    -0.75
     gums
    -0.75
    POSITIVE LOGITS
     situé
    0.59
     laterales
    0.58
    Cubit
    0.55
     inferiores
    0.54
     extensão
    0.54
     sebelah
    0.53
     regione
    0.53
     infantiles
    0.52
     region
    0.52
     regioni
    0.52
    Activations Density 1.033%

    No Known Activations