© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 29146
    Prev
    Next
    INDEX
    Explanations

    syntax elements or metadata related to coding and programming structure

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

    Swift / Objective-C mutating methods

    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
     PC
    -0.42
    ље
    -0.42
    **
    -0.42
    ´
    -0.42
    sel
    -0.40
     ​​
    -0.40
    <bos>
    -0.40
     bomberos
    -0.39
    Id
    -0.39
     Ind
    -0.38
    POSITIVE LOGITS
    GEBURTSDATUM
    1.41
     CreateTagHelper
    1.38
     EconPapers
    1.32
    InjectAttribute
    1.21
     AssemblyCulture
    1.20
    Geplaatst
    1.17
    setVerticalGroup
    1.16
    IUrlHelper
    1.15
     nahilalakip
    1.13
    Autoritní
    1.12
    Activations Density 0.331%

    No Known Activations