© 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. 22-GEMMASCOPE-RES-16K
    11. 2087
    Prev
    Next
    INDEX
    Explanations

    code-related structures and definitions in a programming context

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

    Tokens preceding "class"

    np_acts-logits-general · gemini-2.0-flash

    class definitions or types

    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
     arşivlendi
    -0.49
    perative
    -0.45
    boy
    -0.45
    nonatomic
    -0.44
    ⓧ
    -0.44
    ikyuu
    -0.44
    ftrag
    -0.43
    petition
    -0.43
    ARROLLO
    -0.43
    XtraReports
    -0.42
    POSITIVE LOGITS
     class
    4.17
    class
    3.68
     Class
    3.33
    Class
    3.19
     classes
    2.97
     CLASS
    2.90
     classe
    2.89
     clase
    2.75
     Classes
    2.58
    CLASS
    2.55
    Activations Density 0.341%

    No Known Activations