© 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. 8650
    Prev
    Next
    INDEX
    Explanations

    conditional statements and branching in programming code

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

    Code block's "else" statements

    np_acts-logits-general · gemini-2.0-flash

    else if

    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
     estekak
    -0.67
     Paglinawan
    -0.55
     Cumming
    -0.54
     Maintenant
    -0.54
     فريبيس
    -0.53
    امة
    -0.52
     Takeaway
    -0.52
    ungere
    -0.51
     parfüm
    -0.51
    critto
    -0.51
    POSITIVE LOGITS
     else
    1.18
    else
    1.03
     Else
    0.73
    Else
    0.69
    uxxxx
    0.68
    /*
    0.64
     other
    0.63
     ELSE
    0.61
    MLLoader
    0.61
    batore
    0.60
    Activations Density 0.028%

    No Known Activations