© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1968
    Prev
    Next
    INDEX
    Explanations

    elements related to programming functions and includes in header files

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 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
    🔀
    -0.42
    formik
    -0.40
    SourceChecksum
    -0.37
    TintMode
    -0.35
    ربای
    -0.35
    routeProvider
    -0.35
     brosse
    -0.35
    意的
    -0.35
     fhew
    -0.34
    AnchorTagHelper
    -0.34
    POSITIVE LOGITS
    CppMethod
    0.85
    BeginInit
    0.68
     BrowserModule
    0.68
    BrowserModule
    0.66
    __(/*!
    0.61
     CommonModule
    0.57
    dafx
    0.57
     gynhyrchwyd
    0.56
     FormsModule
    0.53
     AspNetCore
    0.51
    Activations Density 0.890%

    No Known Activations