© 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. 18-GEMMASCOPE-RES-16K
    11. 1942
    Prev
    Next
    INDEX
    Explanations

    initialization of blocks or scales of code

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

    Code inside try-catch blocks

    np_acts-logits-general · gemini-2.0-flash

    try-catch blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Try
    -0.94
    try
    -0.92
     try
    -0.92
    Try
    -0.78
     tries
    -0.73
     attempt
    -0.68
     tried
    -0.66
     TRY
    -0.66
     trying
    -0.65
     Tried
    -0.62
    POSITIVE LOGITS
     виправивши
    0.83
    URLException
    0.73
    UIManager
    0.65
    GEBURTSDATUM
    0.63
    OGND
    0.60
    CodedInputStream
    0.59
    Meld
    0.59
    っぱり
    0.58
    UnusedPrivate
    0.56
     ***!
    0.56
    Activations Density 0.028%

    No Known Activations