© 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. 23-GEMMASCOPE-RES-16K
    11. 12139
    Prev
    Next
    INDEX
    Explanations

    the term "appropriate" and its variations in various contexts throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FailureListener
    -0.52
    Portály
    -0.49
     Ferry
    -0.47
    Ferry
    -0.47
    indata
    -0.45
    Vinc
    -0.45
    Cloud
    -0.45
     Enrollment
    -0.44
     compteur
    -0.43
    Pang
    -0.43
    POSITIVE LOGITS
     appropriate
    1.01
    Appropriate
    0.93
     Appropriate
    0.90
    appropriate
    0.88
    nappropriate
    0.85
     PROPER
    0.83
     suitable
    0.83
     proper
    0.81
     Proper
    0.80
     APPROPRI
    0.78
    Activations Density 0.217%

    No Known Activations