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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10778
    Prev
    Next
    INDEX
    Explanations

    programming and code-related terminologies and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forRoot
    -0.71
     originaux
    -0.68
     montagna
    -0.62
     fatica
    -0.62
     privées
    -0.61
    таратура
    -0.60
     blessés
    -0.59
    kirakan
    -0.59
    værende
    -0.57
     käyttää
    -0.55
    POSITIVE LOGITS
     '{@
    0.71
    存于互联网档案馆
    0.69
    DebuggerNonUser
    0.69
     CreateTagHelper
    0.68
    DebuggerStep
    0.67
     intptr
    0.67
     setw
    0.66
     Sko
    0.65
    AddTagHelper
    0.63
    imetsu
    0.62
    Activations Density 0.233%

    No Known Activations