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. 25-GEMMASCOPE-RES-16K
    6. 6031
    Prev
    Next
    INDEX
    Explanations

    elements related to medical trial processes and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thirty
    -0.59
    ::$_
    -0.58
    ₃
    -0.58
     thirty
    -0.56
     AssemblyVersion
    -0.53
    ///</
    -0.49
     forty
    -0.48
     surla
    -0.48
    getDescriptor
    -0.48
     CanadaChoose
    -0.48
    POSITIVE LOGITS
    httphttps
    0.73
     متعلقه
    0.62
     henvisninger
    0.58
    はじめに
    0.58
     sanitarias
    0.54
     trône
    0.54
    OCCURRED
    0.53
    اریخ
    0.51
     poveznice
    0.51
    Autoritní
    0.50
    Activations Density 0.070%

    No Known Activations