© 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. 7436
    Prev
    Next
    INDEX
    Explanations

    references to health risks and safety precautions

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

    health risks, particularly those related to skin conditions like skin cancer and UV radiation exposure.

    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
    NSArray
    -0.35
    hoben
    -0.31
     fel
    -0.30
     c
    -0.28
    原始内容存档于
    -0.28
     nostrils
    -0.28
     student
    -0.27
     Problem
    -0.27
     dam
    -0.27
     sy
    -0.27
    POSITIVE LOGITS
     sunscreen
    0.90
     Sunscreen
    0.82
    tvguidetime
    0.73
     sunburn
    0.73
     AssemblyCulture
    0.69
    Suns
    0.68
     parasol
    0.66
    windowFixed
    0.65
    şört
    0.64
    ⛱
    0.64
    Activations Density 0.072%

    No Known Activations