© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28527
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structure

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

    previous retrieval

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ModelExpression
    -0.60
    GrantedAuthority
    -0.56
    енча
    -0.56
    Gambas
    -0.55
     okuyayım
    -0.55
    AddTagHelper
    -0.52
     intptr
    -0.52
     DbSet
    -0.50
    vero
    -0.50
    ########.
    -0.50
    POSITIVE LOGITS
     INSTR
    0.55
    EndTag
    0.53
    atsen
    0.52
     Viana
    0.52
     disponibilités
    0.52
    "])){
    0.52
    djangoproject
    0.47
    ssysteme
    0.47
    Ằ
    0.47
    Демографія
    0.46
    Activations Density 0.021%

    No Known Activations