© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 10881
    Prev
    Next
    INDEX
    Explanations

    phrases related to intent and purpose, particularly in the context of moral and legal judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.71
    ContentAsync
    -0.61
    interopRequire
    -0.58
    Personensuche
    -0.57
     defaultstate
    -0.56
    IntoConstraints
    -0.56
    CodedInputStream
    -0.55
    SharedCtor
    -0.55
    kloped
    -0.53
    ReusableCell
    -0.52
    POSITIVE LOGITS
     intention
    0.91
     intentions
    0.91
     intent
    0.81
     intenção
    0.75
     intención
    0.74
     intenciones
    0.73
     Intention
    0.70
    intention
    0.68
     Absicht
    0.66
     Intent
    0.63
    Activations Density 0.533%

    No Known Activations