© 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. 1785
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to risk assessment and management

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

    statistical discussions of risk and risk assessment across various contexts (medical, health, technical, etc.).

    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
    odacty
    -0.58
     muuta
    -0.47
     चाहिए
    -0.47
     laikā
    -0.45
     Tomlinson
    -0.45
    della
    -0.44
    czaj
    -0.44
     Station
    -0.44
     Hecht
    -0.44
     Bout
    -0.43
    POSITIVE LOGITS
     risk
    1.49
    Risk
    1.41
    risk
    1.41
     Risk
    1.37
     risks
    1.30
     RISK
    1.30
    RISK
    1.23
     Risks
    1.19
    risks
    1.13
    Risks
    1.09
    Activations Density 0.059%

    No Known Activations