© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 1820
    Prev
    Next
    INDEX
    Explanations

    phrases related to assurance, quality control, and meeting standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 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
     demurrer
    -0.51
    kegaard
    -0.50
    ArgsConstructor
    -0.48
     suggestion
    -0.48
    almost
    -0.48
     degeneracy
    -0.46
     Almost
    -0.45
     degeneration
    -0.45
    Besch
    -0.45
    waa
    -0.44
    POSITIVE LOGITS
     correct
    0.91
     juiste
    0.91
     proper
    0.88
    correct
    0.86
     correcta
    0.84
     فريبيس
    0.83
     appropriate
    0.81
     properly
    0.80
     riktig
    0.80
     adequate
    0.79
    Activations Density 0.188%

    No Known Activations