© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5115
    Prev
    Next
    INDEX
    Explanations

    loop control variables in programming constructs

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

    programming control flow constructs like loops (for, while) and iteration indices.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    RTDA
    -0.64
    хьтан
    -0.63
    IUrlHelper
    -0.60
     ویکی‌پدی
    -0.58
     MainAxisSize
    -0.57
    Derbyniad
    -0.57
     $_(
    -0.57
     snippetHide
    -0.56
    GEBURTS
    -0.56
    lapsingToolbar
    -0.55
    POSITIVE LOGITS
     NSCoder
    0.41
     للاسماء
    0.38
    fordern
    0.37
    didSet
    0.37
    complexContent
    0.35
     trouvez
    0.35
     traités
    0.34
    Each
    0.34
    Name
    0.34
    Quiénes
    0.33
    Activations Density 0.039%

    No Known Activations