© 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. 1174
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "generate" and its variations

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

    technical terms related to generating or creating something in a computational or technical context, particularly involving coding, processing, or signal generation.

    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
    näm
    -0.48
    topRight
    -0.45
     onClose
    -0.44
     pestaña
    -0.42
    reloj
    -0.42
    Stack
    -0.42
    ciaal
    -0.41
     paja
    -0.41
     étro
    -0.41
    nodeValue
    -0.41
    POSITIVE LOGITS
    generate
    1.02
     generator
    1.00
     generate
    0.99
    generation
    0.94
     generation
    0.94
     Generators
    0.93
     generated
    0.92
     generators
    0.91
     Generate
    0.91
     Generator
    0.91
    Activations Density 0.090%

    No Known Activations