© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12801
    Prev
    Next
    INDEX
    Explanations

    instances of the word "should" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dengar
    -0.44
    cei
    -0.39
     Cowan
    -0.38
    addKeyListener
    -0.35
     Vaux
    -0.35
    NonNull
    -0.35
    AnimationsModule
    -0.35
    batu
    -0.35
    iler
    -0.35
     Einkommen
    -0.34
    POSITIVE LOGITS
     should
    3.55
    Should
    3.50
     Should
    3.41
    should
    3.41
     SHOULD
    2.78
    hould
    2.61
     fhould
    2.52
     debería
    2.31
     sollten
    2.30
     sollte
    2.28
    Activations Density 0.073%

    No Known Activations