© 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. 13-GEMMASCOPE-RES-65K
    6. 56071
    Prev
    Next
    INDEX
    Explanations

    phrases related to inquiry and the origins of specific concepts or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     li
    -0.45
    kelt
    -0.43
     autorytatywna
    -0.41
     only
    -0.40
    sella
    -0.40
     Monteiro
    -0.40
    Only
    -0.40
     mesmo
    -0.39
    Speed
    -0.39
    či
    -0.38
    POSITIVE LOGITS
    SharedDtor
    1.02
     oprot
    0.81
    HostException
    0.78
    帖最后由
    0.73
    exactly
    0.71
     EconPapers
    0.71
     exactly
    0.71
     Exactly
    0.69
    发表于
    0.68
     typelib
    0.68
    Activations Density 0.175%

    No Known Activations