© 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. 0-GEMMASCOPE-RES-16K
    6. 9022
    Prev
    Next
    INDEX
    Explanations

    terms related to safety in clinical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auto
    -0.49
    oro
    -0.48
    lin
    -0.47
     Chase
    -0.47
    ts
    -0.47
    link
    -0.46
    ↵↵
    -0.46
    acy
    -0.46
    ↵
    -0.45
     Lynch
    -0.45
    POSITIVE LOGITS
     safest
    1.01
     safer
    0.97
     bezpeč
    0.92
     bezpiecz
    0.87
    safety
    0.86
     safety
    0.83
     veiligheid
    0.83
     myſelf
    0.79
    Safety
    0.74
    <unused52>
    0.74
    Activations Density 0.247%

    No Known Activations