© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12789
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.69
    ChildScrollView
    -0.67
     IBOutlet
    -0.63
     disambiguazione
    -0.60
    IBOutlet
    -0.58
    GEBURTSDATUM
    -0.58
     Houſe
    -0.56
     pleaſure
    -0.56
    ſelf
    -0.56
    SourceChecksum
    -0.54
    POSITIVE LOGITS
    transQ
    0.52
     surla
    0.42
     Wicidata
    0.35
    CppMethod
    0.35
    ulemon
    0.34
    hdys
    0.33
    ษัท
    0.32
     espalda
    0.31
     sizin
    0.31
     sor
    0.31
    Activations Density 0.257%

    No Known Activations