© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4096
    Prev
    Next
    INDEX
    Explanations

    phrases focusing on the concept of reduction or minimizing various impacts

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

    words and phrases related to reduction or minimizing something.

    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
     trå
    -0.60
    ────────
    -0.55
     startY
    -0.55
    textAlignment
    -0.52
     antennas
    -0.51
     StringTokenizer
    -0.51
    topRight
    -0.50
    tellations
    -0.49
    NAMES
    -0.49
    Сы
    -0.49
    POSITIVE LOGITS
     reduced
    0.90
     reduce
    0.88
     Reduce
    0.84
     Reduced
    0.83
     reduction
    0.83
    Reduced
    0.82
     reducir
    0.82
    reduced
    0.80
    reduce
    0.79
    Reduce
    0.77
    Activations Density 0.106%

    No Known Activations