© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8128
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of value and valuation of life, well-being, or cherished principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    postsleuth
    -0.47
    expandindo
    -0.45
     aggressive
    -0.45
    BufferException
    -0.42
    Aggressive
    -0.41
    principalTable
    -0.40
     Aggressive
    -0.40
    fjspx
    -0.40
     rumor
    -0.40
    Mnemonic
    -0.39
    POSITIVE LOGITS
     valued
    1.00
     treasured
    0.92
     cherished
    0.86
     prized
    0.84
     precious
    0.83
    valued
    0.80
    precious
    0.75
     précieux
    0.75
     cherish
    0.73
     waarde
    0.72
    Activations Density 0.236%

    No Known Activations