© 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. 0-GEMMASCOPE-RES-16K
    11. 15279
    Prev
    Next
    INDEX
    Explanations

    the word "should" and its variants, indicating deliberation or advice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     must
    -0.89
    Must
    -0.89
    must
    -0.87
     Must
    -0.85
    MUST
    -0.69
    twimg
    -0.62
     приходится
    -0.58
    必须
    -0.57
     MUST
    -0.55
     måste
    -0.50
    POSITIVE LOGITS
     should
    2.84
    Should
    2.75
     Should
    2.72
    should
    2.58
     debería
    2.19
     deberían
    2.11
     devrait
    2.09
     devraient
    2.09
     SHOULD
    2.08
     fhould
    2.03
    Activations Density 0.238%

    No Known Activations