© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14620
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming logic

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

    Code conditionals: "else" and "otherwise"

    np_acts-logits-general · gemini-2.0-flash

    else or otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Avic
    -0.59
    quiao
    -0.57
    __*/
    -0.57
     PPD
    -0.56
    Kag
    -0.54
     PNC
    -0.54
    modity
    -0.53
    ifilm
    -0.52
     snippetHide
    -0.51
    MAM
    -0.51
    POSITIVE LOGITS
    else
    1.38
     else
    1.06
     ELSE
    0.93
     Else
    0.92
    Else
    0.90
    ELSE
    0.81
    elif
    0.80
     Otherwise
    0.75
    Otherwise
    0.73
     OTHERWISE
    0.73
    Activations Density 0.036%

    No Known Activations