© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11743
    Prev
    Next
    INDEX
    Explanations

    terms related to safety and safe practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retudo
    -0.43
    ASTNode
    -0.42
    レーション
    -0.38
     wireType
    -0.38
    sequelize
    -0.38
     penas
    -0.37
    writerow
    -0.36
    ellate
    -0.36
     matéria
    -0.36
    MemoryStream
    -0.36
    POSITIVE LOGITS
     Safe
    1.07
    Safe
    1.04
     SAFE
    0.99
    Safety
    0.98
     safe
    0.95
    safe
    0.95
    SAFE
    0.93
     Safety
    0.91
    SAFETY
    0.90
    saf
    0.90
    Activations Density 0.103%

    No Known Activations