© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14343
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structures, particularly related to threading and exception handling in programming

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

    Code snippets with try-catch blocks

    np_acts-logits-general · gemini-2.0-flash

    try blocks or constructs

    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
    ----</
    -0.81
    EDEFAULT
    -0.76
    AddTagHelper
    -0.69
     Roskov
    -0.69
    ungkin
    -0.68
     presumably
    -0.66
    try
    -0.61
    ("")]
    
    -0.61
    +#+#
    -0.59
     архивлан
    -0.58
    POSITIVE LOGITS
    UIManager
    0.66
    Thread
    0.57
    ynchronously
    0.57
    chero
    0.53
     documentaire
    0.53
    TimeUnit
    0.52
    konzert
    0.50
    èlement
    0.48
    spesies
    0.48
    mantel
    0.48
    Activations Density 0.030%

    No Known Activations