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 - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28510
    Prev
    Next
    INDEX
    Explanations

    programming documentation annotations and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.69
     esboço
    -0.63
     protoimpl
    -0.54
     Loretta
    -0.52
    Geplaatst
    -0.51
    CreateModel
    -0.50
    ometal
    -0.50
    сель
    -0.50
     UnityEditor
    -0.48
    strconv
    -0.48
    POSITIVE LOGITS
    ')){
    0.83
    "])){
    0.74
    )">
    0.73
    </caption>
    0.71
    ">${
    0.70
    .")]
    0.70
    '])){
    0.69
    ']){
    0.68
    ']],
    0.68
    '/>
    0.67
    Activations Density 0.012%

    No Known Activations