© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10000
    Prev
    Next
    INDEX
    Explanations

    code structures that define properties and methods in a programming context

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

    Code syntax, especially curly braces and "get"

    np_acts-logits-general · gemini-2.0-flash

    getter and gamma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OpenHelper
    -0.50
     gond
    -0.49
     sust
    -0.48
    stdc
    -0.46
    ChildScrollView
    -0.46
     missed
    -0.46
    _{*}
    -0.46
    optionalTypeArgs
    -0.45
    maiden
    -0.45
    iteln
    -0.45
    POSITIVE LOGITS
    complexContent
    0.64
    Lähteet
    0.59
     kasarigan
    0.59
    InSection
    0.58
    snapshots
    0.52
     getter
    0.52
    featureID
    0.51
    GeoNames
    0.51
     Gattung
    0.51
    CrossRef
    0.51
    Activations Density 0.094%

    No Known Activations