© 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. 24-GEMMASCOPE-RES-16K
    11. 7407
    Prev
    Next
    INDEX
    Explanations

    code related to file existence checks and error handling in file operations

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

    Code comments

    np_acts-logits-general · gemini-2.0-flash

    ring where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (#
    -0.65
    клопе
    -0.63
    KommentareTeilen
    -0.61
     constexpr
    -0.60
    #,
    -0.60
    /#
    -0.57
     Himo
    -0.56
     const
    -0.56
     readonly
    -0.56
     noqa
    -0.55
    POSITIVE LOGITS
    System
    2.11
     System
    1.88
     SYSTEM
    1.16
     system
    1.12
     Systems
    1.02
     Syst
    1.01
    ystem
    1.00
    system
    0.94
     Sistem
    0.92
    SYSTEM
    0.90
    Activations Density 0.086%

    No Known Activations